{"as_of":"2026-08-19T00:35:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:67c681b635bced9c64178cbe6d521bbd78b69e0055e99077e318786f4d4f60a2","coverage":[{"denominator":86,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":86,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T13:24:06.333781Z","state":"measured"},{"denominator":86,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":86,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-18T06:34:40.430872+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2505.21943/citation-record","integrity":"/paper/2505.21943/integrity","json":"/paper/2505.21943/citation-record.json","paper":"/paper/2505.21943"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:23:57.899089Z","title":"Localization in the crowd with topological con- straints","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.21943","last_updated":"2025-05-28T03:53:08Z","snapshot_observed_at":"2026-08-16T04:24:31.601514Z","submitted_at":"2025-05-28T03:53:08Z","title":"Point-to-Region Loss for Semi-Supervised Point-Based Crowd Counting","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-07T13:23:57.899089Z"},"links":{"citing_paper":"/paper/2505.21943"},"observation_digest":"sha256:295ebe9c1056fbd418abc9de51b0eee8ed9cde16b782f657340c9731e3096add","observation_id":"c0243e48-16ac-4139-ab58-5372b8459cea","resolution":{"observed_at":"2026-08-07T13:23:57.899089Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:23:57.981383Z","title":"Anomalous event detection and localization in dense crowd scenes.Mul- timedia Tools and Applications, 82(10):15673–15694, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.21943","last_updated":"2025-05-28T03:53:08Z","snapshot_observed_at":"2026-08-16T04:24:31.601514Z","submitted_at":"2025-05-28T03:53:08Z","title":"Point-to-Region Loss for Semi-Supervised Point-Based Crowd Counting","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-07T13:23:57.981383Z"},"links":{"citing_paper":"/paper/2505.21943"},"observation_digest":"sha256:4a70bef4d8582f861d3c7736660062da45c9c8c7dc5b670cc373bc37ebb80444","observation_id":"91c79937-8701-4c11-b978-d60e97706599","resolution":{"observed_at":"2026-08-07T13:23:57.981383Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:23:58.086226Z","title":"Switching convolutional neural network for crowd counting","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2505.21943","last_updated":"2025-05-28T03:53:08Z","snapshot_observed_at":"2026-08-16T04:24:31.601514Z","submitted_at":"2025-05-28T03:53:08Z","title":"Point-to-Region Loss for Semi-Supervised Point-Based Crowd Counting","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-07T13:23:58.086226Z"},"links":{"citing_paper":"/paper/2505.21943"},"observation_digest":"sha256:102ba591b8c4f871d052f2d58285c66457180e515acc75030a610d61faa8a9a2","observation_id":"5c8eec66-cd9a-452f-bf1a-8dae2ec6d5ab","resolution":{"observed_at":"2026-08-07T13:23:58.086226Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:23:58.178409Z","title":"Bayesian poisson regression for crowd counting","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.21943","last_updated":"2025-05-28T03:53:08Z","snapshot_observed_at":"2026-08-16T04:24:31.601514Z","submitted_at":"2025-05-28T03:53:08Z","title":"Point-to-Region Loss for Semi-Supervised Point-Based Crowd Counting","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-07T13:23:58.178409Z"},"links":{"citing_paper":"/paper/2505.21943"},"observation_digest":"sha256:4c4527b1894d038eee17e05b4976f8db6581e12851e2d4be3f84c7eeaad45389","observation_id":"efedd5a3-7207-4269-8cd4-8945f55599d8","resolution":{"observed_at":"2026-08-07T13:23:58.178409Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:23:58.283042Z","title":"Counting people with low-level features and bayesian regression.IEEE Trans- actions on image processing, 21(4):2160–2177, 2011","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2505.21943","last_updated":"2025-05-28T03:53:08Z","snapshot_observed_at":"2026-08-16T04:24:31.601514Z","submitted_at":"2025-05-28T03:53:08Z","title":"Point-to-Region Loss for Semi-Supervised Point-Based Crowd Counting","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-07T13:23:58.283042Z"},"links":{"citing_paper":"/paper/2505.21943"},"observation_digest":"sha256:54f36a16429c387bdde9cdb3bc6dd18f3d8d562625ec6d29734091ec9f6c7ef2","observation_id":"c521c2e8-11ff-4a72-ad71-da6c07002f86","resolution":{"observed_at":"2026-08-07T13:23:58.283042Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:23:58.420541Z","title":"Privacy preserving crowd monitoring: Counting peo- ple without people models or tracking","venue":null,"work_id":null,"year":2008},"citing_paper":{"arxiv_id":"2505.21943","last_updated":"2025-05-28T03:53:08Z","snapshot_observed_at":"2026-08-16T04:24:31.601514Z","submitted_at":"2025-05-28T03:53:08Z","title":"Point-to-Region Loss for Semi-Supervised Point-Based Crowd Counting","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-07T13:23:58.420541Z"},"links":{"citing_paper":"/paper/2505.21943"},"observation_digest":"sha256:0cb7589a0aa24037a91ce920586917ee7e32c99eacb030fa4ac464ae7a873ef1","observation_id":"bf4151d6-3c18-407c-b6c9-702c1895fda4","resolution":{"observed_at":"2026-08-07T13:23:58.420541Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:24:20.176965Z","title":"Anchor-based group detection in crowd scenes","venue":null,"work_id":"2d1e3409-3de8-4748-99a0-5833edfcac1b","year":2017},"citing_paper":{"arxiv_id":"2505.21943","last_updated":"2025-05-28T03:53:08Z","snapshot_observed_at":"2026-08-16T04:24:31.601514Z","submitted_at":"2025-05-28T03:53:08Z","title":"Point-to-Region Loss for Semi-Supervised Point-Based Crowd Counting","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-07T13:23:58.525666Z"},"links":{"citing_paper":"/paper/2505.21943"},"observation_digest":"sha256:88c559c4b0248dc710fb4472e1b08635309386d1fa47782b1b466b11d7d5ce5b","observation_id":"c685a124-8a48-4734-9894-c9ea50ef70be","resolution":{"observed_at":"2026-08-07T13:24:20.224379Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:24:20.031774Z","title":"Rethinking spatial invariance of convolutional networks for object counting","venue":null,"work_id":"67aa23db-6748-41a6-bcf4-319e6e22ae33","year":2022},"citing_paper":{"arxiv_id":"2505.21943","last_updated":"2025-05-28T03:53:08Z","snapshot_observed_at":"2026-08-16T04:24:31.601514Z","submitted_at":"2025-05-28T03:53:08Z","title":"Point-to-Region Loss for Semi-Supervised Point-Based Crowd Counting","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-07T13:23:58.608579Z"},"links":{"citing_paper":"/paper/2505.21943"},"observation_digest":"sha256:c4763f8692c8344179801930c3ffe1b999a5bcb9b35db18eeba0be0a0b9f514b","observation_id":"71e9c19e-fcf6-436d-b164-cbd9475afc86","resolution":{"observed_at":"2026-08-07T13:24:20.107502Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2012.04164","last_updated":"2022-10-12T01:09:38Z","snapshot_observed_at":"2026-08-16T19:00:15.272176Z","submitted_at":"2020-12-08T02:17:19Z","title":"Learning Independent Instance Maps for Crowd Localization","version":3},"cited_work":{"arxiv_id":"2012.04164","doi":null,"metadata_source":"pith","pith_arxiv_id":"2012.04164","snapshot_observed_at":"2026-08-07T13:24:06.658303Z","title":"Learning Independent Instance Maps for Crowd Localization","venue":"cs.CV","work_id":"9c5bf4d7-be15-4012-84fd-94f11e0ed980","year":2020},"citing_paper":{"arxiv_id":"2505.21943","last_updated":"2025-05-28T03:53:08Z","snapshot_observed_at":"2026-08-16T04:24:31.601514Z","submitted_at":"2025-05-28T03:53:08Z","title":"Point-to-Region Loss for Semi-Supervised Point-Based Crowd Counting","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-07T13:23:58.727395Z"},"links":{"cited_paper":"/paper/2012.04164","citing_paper":"/paper/2505.21943"},"observation_digest":"sha256:4655632a9a2ed69f8174983f90470ced43dd44a106ba7c83ac51d6bb77dc18e8","observation_id":"0b5a907f-c8d2-40ae-ae51-89f51ba711ae","resolution":{"observed_at":"2026-08-07T13:24:06.745017Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:24:19.911367Z","title":"Steerer: Resolving scale variations for counting and localization via selective inheritance learning","venue":null,"work_id":"8e09c076-9993-485d-8f43-20162a3f6ad9","year":2023},"citing_paper":{"arxiv_id":"2505.21943","last_updated":"2025-05-28T03:53:08Z","snapshot_observed_at":"2026-08-16T04:24:31.601514Z","submitted_at":"2025-05-28T03:53:08Z","title":"Point-to-Region Loss for Semi-Supervised Point-Based Crowd Counting","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-07T13:23:58.840387Z"},"links":{"citing_paper":"/paper/2505.21943"},"observation_digest":"sha256:f8902c29a63fc97763854ff52f2a80b8254fcbf20fcf0f1a1237f172516a1422","observation_id":"bfa8fd09-ca59-49bf-855f-a3b5f204711d","resolution":{"observed_at":"2026-08-07T13:24:19.960982Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:24:19.754071Z","title":"Error-aware density isomorphism re- construction for unsupervised cross-domain crowd counting","venue":null,"work_id":"5380b826-6e4a-4d22-8ec8-9c16aa418bcf","year":2021},"citing_paper":{"arxiv_id":"2505.21943","last_updated":"2025-05-28T03:53:08Z","snapshot_observed_at":"2026-08-16T04:24:31.601514Z","submitted_at":"2025-05-28T03:53:08Z","title":"Point-to-Region Loss for Semi-Supervised Point-Based Crowd Counting","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-07T13:23:58.935237Z"},"links":{"citing_paper":"/paper/2505.21943"},"observation_digest":"sha256:324b42618c7c49cb3224c223879be6d1c649198ff069da20915d18777f3df1a3","observation_id":"620cc26c-fed2-4865-854d-48c085db6f2b","resolution":{"observed_at":"2026-08-07T13:24:19.837160Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:24:19.635454Z","title":"Composition loss for counting, density map estima- tion and localization in dense crowds","venue":null,"work_id":"b3404a36-7b5c-4f7d-bf7d-bd6e6c4a97ee","year":2018},"citing_paper":{"arxiv_id":"2505.21943","last_updated":"2025-05-28T03:53:08Z","snapshot_observed_at":"2026-08-16T04:24:31.601514Z","submitted_at":"2025-05-28T03:53:08Z","title":"Point-to-Region Loss for Semi-Supervised Point-Based Crowd Counting","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-07T13:23:59.029324Z"},"links":{"citing_paper":"/paper/2505.21943"},"observation_digest":"sha256:68e7ca050c09c6a8c48e6ba350f2093d1c73a5a9ae7255158bf4d8a9d462634a","observation_id":"c990206a-99ac-423d-b1ea-9d49b80cc47e","resolution":{"observed_at":"2026-08-07T13:24:19.686437Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:24:19.456633Z","title":"Ex- plaining convolutional neural networks using softmax gra- dient layer-wise relevance propagation","venue":null,"work_id":"aaffa511-c41f-41df-a823-3e3c5ccb5e80","year":2019},"citing_paper":{"arxiv_id":"2505.21943","last_updated":"2025-05-28T03:53:08Z","snapshot_observed_at":"2026-08-16T04:24:31.601514Z","submitted_at":"2025-05-28T03:53:08Z","title":"Point-to-Region Loss for Semi-Supervised Point-Based Crowd Counting","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-07T13:23:59.143722Z"},"links":{"citing_paper":"/paper/2505.21943"},"observation_digest":"sha256:6efe63e12b81943249d6884cadd2d2c70df89b41c2749e7afd175e996c5d62fc","observation_id":"2dd8c908-f1b3-452a-967c-50fe7a39e88b","resolution":{"observed_at":"2026-08-07T13:24:19.530512Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:24:19.299143Z","title":"Clip- count: Towards text-guided zero-shot object counting","venue":null,"work_id":"407f0f9b-b9f2-488b-808f-d6d91b8ab876","year":2023},"citing_paper":{"arxiv_id":"2505.21943","last_updated":"2025-05-28T03:53:08Z","snapshot_observed_at":"2026-08-16T04:24:31.601514Z","submitted_at":"2025-05-28T03:53:08Z","title":"Point-to-Region Loss for Semi-Supervised Point-Based Crowd Counting","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-07T13:23:59.235664Z"},"links":{"citing_paper":"/paper/2505.21943"},"observation_digest":"sha256:4b702fe53a5abef4a8a852ebd3f78a60ed3e8e608f2438f743d90c843ad99bd4","observation_id":"1abff886-ead7-49b1-a141-41b4af021592","resolution":{"observed_at":"2026-08-07T13:24:19.366975Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:24:19.178426Z","title":"Pseudo-label: The simple and effi- cient semi-supervised learning method for deep neural net- works","venue":null,"work_id":"05780d5b-751f-40e2-b6e5-085716de963c","year":2013},"citing_paper":{"arxiv_id":"2505.21943","last_updated":"2025-05-28T03:53:08Z","snapshot_observed_at":"2026-08-16T04:24:31.601514Z","submitted_at":"2025-05-28T03:53:08Z","title":"Point-to-Region Loss for Semi-Supervised Point-Based Crowd Counting","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-07T13:23:59.338595Z"},"links":{"citing_paper":"/paper/2505.21943"},"observation_digest":"sha256:aa786ac4342ed64ee913fb51f51bac902c0604238916b177881154465f889899","observation_id":"2efbeb34-629c-42bd-82c0-0c42918b7f11","resolution":{"observed_at":"2026-08-07T13:24:19.230892Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:24:19.070594Z","title":"Pedes- trian detection in crowded scenes","venue":null,"work_id":"2c10504a-0519-46bc-be46-f6d0f3810c28","year":2005},"citing_paper":{"arxiv_id":"2505.21943","last_updated":"2025-05-28T03:53:08Z","snapshot_observed_at":"2026-08-16T04:24:31.601514Z","submitted_at":"2025-05-28T03:53:08Z","title":"Point-to-Region Loss for Semi-Supervised Point-Based Crowd Counting","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-07T13:23:59.450016Z"},"links":{"citing_paper":"/paper/2505.21943"},"observation_digest":"sha256:2e226df3cb551347c02ab200331cee56ea973ad2a21ab66a730b30b337a5ff25","observation_id":"c8cf8d2a-d574-48cc-9b7e-448623bfb1f8","resolution":{"observed_at":"2026-08-07T13:24:19.117756Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:24:18.960767Z","title":"Learning to count objects in images.Advances in neural information process- ing systems, 23, 2010","venue":null,"work_id":"fd3ae8c4-6984-413a-98d2-f669ffc0f09f","year":2010},"citing_paper":{"arxiv_id":"2505.21943","last_updated":"2025-05-28T03:53:08Z","snapshot_observed_at":"2026-08-16T04:24:31.601514Z","submitted_at":"2025-05-28T03:53:08Z","title":"Point-to-Region Loss for Semi-Supervised Point-Based Crowd Counting","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-07T13:23:59.513556Z"},"links":{"citing_paper":"/paper/2505.21943"},"observation_digest":"sha256:994e5efad648092040d0f634672151b3afae4212f3c5d767daf413720e6627f0","observation_id":"ed8570d5-fcb8-46c4-aa14-adcbc6441028","resolution":{"observed_at":"2026-08-07T13:24:19.013201Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:24:18.828142Z","title":"Calibrating uncertainty for semi-supervised crowd counting","venue":null,"work_id":"0111ca99-8764-478d-8c9e-f019266bc1bd","year":2023},"citing_paper":{"arxiv_id":"2505.21943","last_updated":"2025-05-28T03:53:08Z","snapshot_observed_at":"2026-08-16T04:24:31.601514Z","submitted_at":"2025-05-28T03:53:08Z","title":"Point-to-Region Loss for Semi-Supervised Point-Based Crowd Counting","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-07T13:23:59.629508Z"},"links":{"citing_paper":"/paper/2505.21943"},"observation_digest":"sha256:d4f00584829ced9341c8de064a652b552c007f8363bbe5c8c23e3cddd19dc325","observation_id":"cb902dc8-d7c1-4f1d-9417-a3e975cea112","resolution":{"observed_at":"2026-08-07T13:24:18.905706Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:24:18.683325Z","title":"Semi- supervised crowd counting based on hard pseudo-labels","venue":null,"work_id":"a8d52694-2eb8-43db-96ea-2d0b28dc138b","year":2024},"citing_paper":{"arxiv_id":"2505.21943","last_updated":"2025-05-28T03:53:08Z","snapshot_observed_at":"2026-08-16T04:24:31.601514Z","submitted_at":"2025-05-28T03:53:08Z","title":"Point-to-Region Loss for Semi-Supervised Point-Based Crowd Counting","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-07T13:23:59.776372Z"},"links":{"citing_paper":"/paper/2505.21943"},"observation_digest":"sha256:f36144e2a5d7d6a75be6c4067fb54d592c7b6c63d542bf49e1a065baee87e2cf","observation_id":"b4d0cee3-25d3-412c-bba4-625c6567c698","resolution":{"observed_at":"2026-08-07T13:24:18.762431Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:24:18.538924Z","title":"Csrnet: Di- lated convolutional neural networks for understanding the highly congested scenes","venue":null,"work_id":"892d2eb7-9190-478e-94e4-3c65c0d75594","year":2018},"citing_paper":{"arxiv_id":"2505.21943","last_updated":"2025-05-28T03:53:08Z","snapshot_observed_at":"2026-08-16T04:24:31.601514Z","submitted_at":"2025-05-28T03:53:08Z","title":"Point-to-Region Loss for Semi-Supervised Point-Based Crowd Counting","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-07T13:23:59.915500Z"},"links":{"citing_paper":"/paper/2505.21943"},"observation_digest":"sha256:d29cbb369d52dc0e3dcc5932609bccf01426263d284be3897e9f44bf997bd46c","observation_id":"d8c5319e-d478-46cc-8bb1-79037834bb8d","resolution":{"observed_at":"2026-08-07T13:24:18.605035Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:24:18.388698Z","title":"An end-to-end transformer model for crowd localization","venue":null,"work_id":"a3fd8f0a-1853-40b6-9f76-8bf14d7865fa","year":2022},"citing_paper":{"arxiv_id":"2505.21943","last_updated":"2025-05-28T03:53:08Z","snapshot_observed_at":"2026-08-16T04:24:31.601514Z","submitted_at":"2025-05-28T03:53:08Z","title":"Point-to-Region Loss for Semi-Supervised Point-Based Crowd Counting","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:00.017730Z"},"links":{"citing_paper":"/paper/2505.21943"},"observation_digest":"sha256:04f72158db8787e92f6894e758b5d32b6239f988cd0bc78c0d30736ae8469fbc","observation_id":"df1b2c8a-6157-40b4-afde-926c6de53c6d","resolution":{"observed_at":"2026-08-07T13:24:18.460752Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:24:18.217097Z","title":"Direct measure matching for crowd counting","venue":null,"work_id":"5418d2ef-96a7-4e95-b80e-28ee42eec573","year":2021},"citing_paper":{"arxiv_id":"2505.21943","last_updated":"2025-05-28T03:53:08Z","snapshot_observed_at":"2026-08-16T04:24:31.601514Z","submitted_at":"2025-05-28T03:53:08Z","title":"Point-to-Region Loss for Semi-Supervised Point-Based Crowd Counting","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:00.111719Z"},"links":{"citing_paper":"/paper/2505.21943"},"observation_digest":"sha256:72a53cbec6d6c329214227e32314e3b859736b0f2a1f804f8599ec6679c88167","observation_id":"24b363e0-13ae-45c9-91fa-dfc15a83731b","resolution":{"observed_at":"2026-08-07T13:24:18.311530Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:24:18.071488Z","title":"Semi-supervised crowd counting via density agency","venue":null,"work_id":"2d2bcca2-c79e-4768-a40a-20f23d7e1aa3","year":2022},"citing_paper":{"arxiv_id":"2505.21943","last_updated":"2025-05-28T03:53:08Z","snapshot_observed_at":"2026-08-16T04:24:31.601514Z","submitted_at":"2025-05-28T03:53:08Z","title":"Point-to-Region Loss for Semi-Supervised Point-Based Crowd Counting","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:00.216810Z"},"links":{"citing_paper":"/paper/2505.21943"},"observation_digest":"sha256:ca6e96603edca8fb3a5349e7dbfc14561a87df84318eecc69c71958a138647c9","observation_id":"cc866c13-121c-4847-9f4b-eb5faa44058d","resolution":{"observed_at":"2026-08-07T13:24:18.138424Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:24:17.920951Z","title":"Boosting crowd counting via multifaceted attention","venue":null,"work_id":"552d9661-f073-47a7-a327-3d20bfaf90c8","year":2022},"citing_paper":{"arxiv_id":"2505.21943","last_updated":"2025-05-28T03:53:08Z","snapshot_observed_at":"2026-08-16T04:24:31.601514Z","submitted_at":"2025-05-28T03:53:08Z","title":"Point-to-Region Loss for Semi-Supervised Point-Based Crowd Counting","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:00.351195Z"},"links":{"citing_paper":"/paper/2505.21943"},"observation_digest":"sha256:804f2efbcbc545e8d06bca4484cdd42b6cc703d6451fcd8d13308464e44636cd","observation_id":"89d81023-969c-4bbd-9fc6-ac1485db7c6c","resolution":{"observed_at":"2026-08-07T13:24:18.001565Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.15297","last_updated":"2024-02-23T12:48:02Z","snapshot_observed_at":"2026-08-16T14:15:55.079990Z","submitted_at":"2024-02-23T12:48:02Z","title":"Semi-supervised Counting via Pixel-by-pixel Density Distribution Modelling","version":1},"cited_work":{"arxiv_id":"2402.15297","doi":null,"metadata_source":"pith","pith_arxiv_id":"2402.15297","snapshot_observed_at":"2026-08-07T13:24:06.459870Z","title":"Semi-supervised Counting via Pixel-by-pixel Density Distribution Modelling","venue":"cs.CV","work_id":"433ac769-6c15-4f3f-9824-cde75be8bb61","year":2024},"citing_paper":{"arxiv_id":"2505.21943","last_updated":"2025-05-28T03:53:08Z","snapshot_observed_at":"2026-08-16T04:24:31.601514Z","submitted_at":"2025-05-28T03:53:08Z","title":"Point-to-Region Loss for Semi-Supervised Point-Based Crowd Counting","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:00.434803Z"},"links":{"cited_paper":"/paper/2402.15297","citing_paper":"/paper/2505.21943"},"observation_digest":"sha256:229cac4063dbc73576bd7aa9c02087beca1a38afaff3df3e7d1a0c7beea149b1","observation_id":"de31bc4a-ae02-4adb-8368-86282699b766","resolution":{"observed_at":"2026-08-07T13:24:06.547982Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:24:17.757102Z","title":"Optimal transport mini- mization: Crowd localization on density maps for semi- supervised counting","venue":null,"work_id":"a66751a4-03a5-4ac9-a6c0-97920570d523","year":2023},"citing_paper":{"arxiv_id":"2505.21943","last_updated":"2025-05-28T03:53:08Z","snapshot_observed_at":"2026-08-16T04:24:31.601514Z","submitted_at":"2025-05-28T03:53:08Z","title":"Point-to-Region Loss for Semi-Supervised Point-Based Crowd Counting","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:00.513206Z"},"links":{"citing_paper":"/paper/2505.21943"},"observation_digest":"sha256:e39c2bc57e34f779d09297af56be5c2fa66c2a3bda77feb8decb234d0e67197c","observation_id":"2c04b7f4-c67f-414e-814e-400e03de6ff3","resolution":{"observed_at":"2026-08-07T13:24:17.858254Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:24:17.603070Z","title":"A fixed-point approach to unified prompt-based counting","venue":null,"work_id":"3efe75aa-ca65-4551-8e43-a307c6b2409e","year":2024},"citing_paper":{"arxiv_id":"2505.21943","last_updated":"2025-05-28T03:53:08Z","snapshot_observed_at":"2026-08-16T04:24:31.601514Z","submitted_at":"2025-05-28T03:53:08Z","title":"Point-to-Region Loss for Semi-Supervised Point-Based Crowd Counting","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:00.601649Z"},"links":{"citing_paper":"/paper/2505.21943"},"observation_digest":"sha256:1878e8098f652d0882ff2fc21bf4ffb69a773c34480e11c83b710ebdc48294cb","observation_id":"fcf7f7b8-20f9-4a14-8a82-978805329579","resolution":{"observed_at":"2026-08-07T13:24:17.668404Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:24:17.426209Z","title":"Proximal mapping loss: Understanding loss functions in crowd counting & lo- calization","venue":null,"work_id":"b2651f30-d36b-480d-8d36-82fb7ad1db96","year":null},"citing_paper":{"arxiv_id":"2505.21943","last_updated":"2025-05-28T03:53:08Z","snapshot_observed_at":"2026-08-16T04:24:31.601514Z","submitted_at":"2025-05-28T03:53:08Z","title":"Point-to-Region Loss for Semi-Supervised Point-Based Crowd Counting","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:00.704249Z"},"links":{"citing_paper":"/paper/2505.21943"},"observation_digest":"sha256:789d34d98c918a12749af0a55e25247825d3ab93ca4a2fdac36b3a501cc0e4c6","observation_id":"64fcfed0-be78-409f-aec5-b64173045900","resolution":{"observed_at":"2026-08-07T13:24:17.526033Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:24:17.225005Z","title":"Learning to detect anomaly events in crowd scenes from synthetic data","venue":null,"work_id":"cb677e0c-abdd-4710-b47c-445b5bab3d34","year":2021},"citing_paper":{"arxiv_id":"2505.21943","last_updated":"2025-05-28T03:53:08Z","snapshot_observed_at":"2026-08-16T04:24:31.601514Z","submitted_at":"2025-05-28T03:53:08Z","title":"Point-to-Region Loss for Semi-Supervised Point-Based Crowd Counting","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:00.793198Z"},"links":{"citing_paper":"/paper/2505.21943"},"observation_digest":"sha256:e650082272b95642753e03a6dc28f561f98c8a78d9b5fcc610dc9ddd63e3f7ce","observation_id":"e62eba8d-26fc-44b5-885c-8e2200f98cb3","resolution":{"observed_at":"2026-08-07T13:24:17.319827Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:24:17.007247Z","title":"Scale- prior deformable convolution for exemplar-guided class- agnostic counting","venue":null,"work_id":"a69d314b-8d6d-4665-8c37-cb6ba1010a35","year":2022},"citing_paper":{"arxiv_id":"2505.21943","last_updated":"2025-05-28T03:53:08Z","snapshot_observed_at":"2026-08-16T04:24:31.601514Z","submitted_at":"2025-05-28T03:53:08Z","title":"Point-to-Region Loss for Semi-Supervised Point-Based Crowd Counting","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:00.888671Z"},"links":{"citing_paper":"/paper/2505.21943"},"observation_digest":"sha256:93eef3112e79a53e31b1937ec6621d312a8d0e645526cc1149c81ed2b27f33f8","observation_id":"c36bc91b-df1d-4216-a232-ffe8d5beb4da","resolution":{"observed_at":"2026-08-07T13:24:17.129523Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:24:16.800447Z","title":"Point-query quadtree for crowd counting, localization, and more","venue":null,"work_id":"a5a00f55-e161-4a44-a008-51049bfaafb0","year":2023},"citing_paper":{"arxiv_id":"2505.21943","last_updated":"2025-05-28T03:53:08Z","snapshot_observed_at":"2026-08-16T04:24:31.601514Z","submitted_at":"2025-05-28T03:53:08Z","title":"Point-to-Region Loss for Semi-Supervised Point-Based Crowd Counting","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:00.996939Z"},"links":{"citing_paper":"/paper/2505.21943"},"observation_digest":"sha256:8ca445792ad2586d34de60c31444560b24cc87266d986af1b84d06781f3bc354","observation_id":"62e37b4a-b523-462e-9ae2-55d401e1d754","resolution":{"observed_at":"2026-08-07T13:24:16.881791Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:24:16.568887Z","title":"Leveraging unlabeled data for crowd counting by learning to rank","venue":null,"work_id":"1cc191b0-cc56-4038-a1fb-59718e64da04","year":2018},"citing_paper":{"arxiv_id":"2505.21943","last_updated":"2025-05-28T03:53:08Z","snapshot_observed_at":"2026-08-16T04:24:31.601514Z","submitted_at":"2025-05-28T03:53:08Z","title":"Point-to-Region Loss for Semi-Supervised Point-Based Crowd Counting","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:01.063629Z"},"links":{"citing_paper":"/paper/2505.21943"},"observation_digest":"sha256:ecb8dfc88f910ea8e3678bdebb38bf286235eea3db08054fecb70aa4a26cedc6","observation_id":"7d925453-0b9d-4085-8023-15c23fb3aa39","resolution":{"observed_at":"2026-08-07T13:24:16.675940Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:24:16.411057Z","title":"Exploiting unlabeled data in cnns by self-supervised learning to rank.IEEE transactions on pattern analysis and machine intelligence, 41(8):1862–1878, 2019","venue":null,"work_id":"e8fcfcc0-180c-488f-a16f-0c52a7057e0e","year":2019},"citing_paper":{"arxiv_id":"2505.21943","last_updated":"2025-05-28T03:53:08Z","snapshot_observed_at":"2026-08-16T04:24:31.601514Z","submitted_at":"2025-05-28T03:53:08Z","title":"Point-to-Region Loss for Semi-Supervised Point-Based Crowd Counting","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:01.183620Z"},"links":{"citing_paper":"/paper/2505.21943"},"observation_digest":"sha256:4f74b03c84083384d648486dd457f449e24efb96361a3c25454ccac7b4b87d99","observation_id":"1f249e0d-7755-4643-9f5e-1e8d851a6b6c","resolution":{"observed_at":"2026-08-07T13:24:16.491529Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:24:16.187152Z","title":"Semi-supervised crowd counting via self-training on surrogate tasks","venue":null,"work_id":"67790563-659e-4ffa-a306-79990e43f7f9","year":2020},"citing_paper":{"arxiv_id":"2505.21943","last_updated":"2025-05-28T03:53:08Z","snapshot_observed_at":"2026-08-16T04:24:31.601514Z","submitted_at":"2025-05-28T03:53:08Z","title":"Point-to-Region Loss for Semi-Supervised Point-Based Crowd Counting","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:01.306979Z"},"links":{"citing_paper":"/paper/2505.21943"},"observation_digest":"sha256:80c4a65ab78ad6d4d357c84a811460932fdf125a4c00292c2594b04c5fd71136","observation_id":"5e6447f1-5693-4239-8572-bb64ec14817e","resolution":{"observed_at":"2026-08-07T13:24:16.302525Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:24:15.956135Z","title":"Towards unsupervised crowd counting via regression-detection bi-knowledge transfer","venue":null,"work_id":"2c8932ab-5f12-4d65-a30b-e7b303c3c891","year":2020},"citing_paper":{"arxiv_id":"2505.21943","last_updated":"2025-05-28T03:53:08Z","snapshot_observed_at":"2026-08-16T04:24:31.601514Z","submitted_at":"2025-05-28T03:53:08Z","title":"Point-to-Region Loss for Semi-Supervised Point-Based Crowd Counting","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:01.397869Z"},"links":{"citing_paper":"/paper/2505.21943"},"observation_digest":"sha256:e8fa964f25ba86b328c738c9338d4f0c403ee5493eef17a9ca95c44bf5c57f67","observation_id":"d1128e9d-7163-4ac9-8243-3c0a02b82296","resolution":{"observed_at":"2026-08-07T13:24:16.054098Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:24:15.754287Z","title":"Semi-supervised crowd counting via multi-task pseudo-label self-correction strategy.IEEE Transactions on Circuits and Systems for Video Technology, 2024","venue":null,"work_id":"8e6c4a7b-a46e-46de-a7cb-2e5688ca24dc","year":2024},"citing_paper":{"arxiv_id":"2505.21943","last_updated":"2025-05-28T03:53:08Z","snapshot_observed_at":"2026-08-16T04:24:31.601514Z","submitted_at":"2025-05-28T03:53:08Z","title":"Point-to-Region Loss for Semi-Supervised Point-Based Crowd Counting","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:01.475876Z"},"links":{"citing_paper":"/paper/2505.21943"},"observation_digest":"sha256:7fb19307ad3dab7823d0b45cb739572daf72812d414907a5c8f46b6e76cb70e7","observation_id":"71badb55-bd3d-49f7-8b13-70d85b2768b5","resolution":{"observed_at":"2026-08-07T13:24:15.844689Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:24:15.536647Z","title":"Counting people crossing a line using integer programming and local features.IEEE Transactions on Circuits and Systems for Video Technology, 26(10):1955–1969, 2015","venue":null,"work_id":"00a10bdf-fe72-404c-bd38-f66b06b6596c","year":1955},"citing_paper":{"arxiv_id":"2505.21943","last_updated":"2025-05-28T03:53:08Z","snapshot_observed_at":"2026-08-16T04:24:31.601514Z","submitted_at":"2025-05-28T03:53:08Z","title":"Point-to-Region Loss for Semi-Supervised Point-Based Crowd Counting","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:01.554566Z"},"links":{"citing_paper":"/paper/2505.21943"},"observation_digest":"sha256:c9d0a64423c3c2ed0516d847aac59c6e5ee8d5e5e889f94b6bc12fbfd5c13178","observation_id":"4318dd8a-72e2-4c1e-8ce0-595b892a901e","resolution":{"observed_at":"2026-08-07T13:24:15.614361Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:24:15.311384Z","title":"Bayesian loss for crowd count estimation with point supervi- sion","venue":null,"work_id":"a69e906c-586d-4fb6-961d-d503baac1e8f","year":2019},"citing_paper":{"arxiv_id":"2505.21943","last_updated":"2025-05-28T03:53:08Z","snapshot_observed_at":"2026-08-16T04:24:31.601514Z","submitted_at":"2025-05-28T03:53:08Z","title":"Point-to-Region Loss for Semi-Supervised Point-Based Crowd Counting","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:01.624533Z"},"links":{"citing_paper":"/paper/2505.21943"},"observation_digest":"sha256:7312ef6bbf808eb1d1689318cb41a5762b91a1ddb92a189151c8c687c61fc7c5","observation_id":"3e40c625-4b18-4fad-a9de-ec4c4ad66a69","resolution":{"observed_at":"2026-08-07T13:24:15.416617Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:24:15.122741Z","title":"Learning to count via unbalanced optimal transport","venue":null,"work_id":"4c055f97-7c04-4e80-a87a-2f7e6b786e09","year":2021},"citing_paper":{"arxiv_id":"2505.21943","last_updated":"2025-05-28T03:53:08Z","snapshot_observed_at":"2026-08-16T04:24:31.601514Z","submitted_at":"2025-05-28T03:53:08Z","title":"Point-to-Region Loss for Semi-Supervised Point-Based Crowd Counting","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:01.729464Z"},"links":{"citing_paper":"/paper/2505.21943"},"observation_digest":"sha256:963c68c3524e965bd0dcccbc90137281de453b85a2c75ff792df48224a2b54b2","observation_id":"a8f5d83f-45bb-4291-a2f0-ccf49a84eff1","resolution":{"observed_at":"2026-08-07T13:24:15.233831Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:24:14.863097Z","title":"Domain generalization via gradient surgery","venue":null,"work_id":"677cccdb-45fa-4e1b-86c1-56548375d5fa","year":2021},"citing_paper":{"arxiv_id":"2505.21943","last_updated":"2025-05-28T03:53:08Z","snapshot_observed_at":"2026-08-16T04:24:31.601514Z","submitted_at":"2025-05-28T03:53:08Z","title":"Point-to-Region Loss for Semi-Supervised Point-Based Crowd Counting","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:01.824225Z"},"links":{"citing_paper":"/paper/2505.21943"},"observation_digest":"sha256:1d3c6a1f532a632fb1e6def916e040ee0c4bc45ec114043d9ba0dfd528b44a94","observation_id":"1e99eb81-65ca-4185-b736-3478c58ccb00","resolution":{"observed_at":"2026-08-07T13:24:14.996196Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:24:14.654936Z","title":"De- tection and tracking of groups in crowd","venue":null,"work_id":"b99ad09a-9149-4b72-92fc-860a7071fe0d","year":2013},"citing_paper":{"arxiv_id":"2505.21943","last_updated":"2025-05-28T03:53:08Z","snapshot_observed_at":"2026-08-16T04:24:31.601514Z","submitted_at":"2025-05-28T03:53:08Z","title":"Point-to-Region Loss for Semi-Supervised Point-Based Crowd Counting","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:01.933205Z"},"links":{"citing_paper":"/paper/2505.21943"},"observation_digest":"sha256:2b1be5f2df64574e6993a7f268357aa22efe365c11be0456896561fdd55b2618","observation_id":"9416dc34-445d-4b7e-bf4d-dec0afed661e","resolution":{"observed_at":"2026-08-07T13:24:14.748826Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:24:14.528748Z","title":"Spa- tial uncertainty-aware semi-supervised crowd counting","venue":null,"work_id":"c79cc7a7-816e-4f9d-8ca0-d35c7675b45f","year":2021},"citing_paper":{"arxiv_id":"2505.21943","last_updated":"2025-05-28T03:53:08Z","snapshot_observed_at":"2026-08-16T04:24:31.601514Z","submitted_at":"2025-05-28T03:53:08Z","title":"Point-to-Region Loss for Semi-Supervised Point-Based Crowd Counting","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:02.051875Z"},"links":{"citing_paper":"/paper/2505.21943"},"observation_digest":"sha256:4973baed415007cb295efc10393530242bcf630cc2ed88efaf88d32ef2c09904","observation_id":"742c468d-5bd3-46df-a035-31dd4e48f788","resolution":{"observed_at":"2026-08-07T13:24:14.599891Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:24:14.418264Z","title":"Single domain general- ization for crowd counting","venue":null,"work_id":"2dc8e914-9372-4f0c-8059-1bbe2cfef8cd","year":2024},"citing_paper":{"arxiv_id":"2505.21943","last_updated":"2025-05-28T03:53:08Z","snapshot_observed_at":"2026-08-16T04:24:31.601514Z","submitted_at":"2025-05-28T03:53:08Z","title":"Point-to-Region Loss for Semi-Supervised Point-Based Crowd Counting","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:02.154944Z"},"links":{"citing_paper":"/paper/2505.21943"},"observation_digest":"sha256:8e89599718e20e5ef884d79915a0623705e5a189b5f56e06a3166ce8d3e8c200","observation_id":"f11e1749-ff6d-45d8-96c3-25b8c4a055ba","resolution":{"observed_at":"2026-08-07T13:24:14.479461Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:24:14.084531Z","title":"Ablation-cam: Visual explanations for deep convolutional network via gradient- free localization","venue":null,"work_id":"bb392fe5-17f8-4213-ba68-93c5835ec93b","year":2020},"citing_paper":{"arxiv_id":"2505.21943","last_updated":"2025-05-28T03:53:08Z","snapshot_observed_at":"2026-08-16T04:24:31.601514Z","submitted_at":"2025-05-28T03:53:08Z","title":"Point-to-Region Loss for Semi-Supervised Point-Based Crowd Counting","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:02.228705Z"},"links":{"citing_paper":"/paper/2505.21943"},"observation_digest":"sha256:c0d9fcddb936c4ccf418c3132d491a9cbcf709ecbd096676583fa1da2917ef9f","observation_id":"53c4f9ea-390f-42ad-a5cc-7abad84866f4","resolution":{"observed_at":"2026-08-07T13:24:14.170448Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:24:13.838825Z","title":"Learning to count everything","venue":null,"work_id":"76cec241-20fa-40ef-9295-f2d77e1c2523","year":2021},"citing_paper":{"arxiv_id":"2505.21943","last_updated":"2025-05-28T03:53:08Z","snapshot_observed_at":"2026-08-16T04:24:31.601514Z","submitted_at":"2025-05-28T03:53:08Z","title":"Point-to-Region Loss for Semi-Supervised Point-Based Crowd Counting","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:02.334555Z"},"links":{"citing_paper":"/paper/2505.21943"},"observation_digest":"sha256:89b79b1269c6a2b4a3d8ad1c52fde7d464b28d26e560562588e92948ccfec881","observation_id":"9fd616e0-f37a-4b83-9e1f-4c1d899671db","resolution":{"observed_at":"2026-08-07T13:24:13.964601Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:24:13.543553Z","title":"Tracking-by-counting: Using network flows on crowd density maps for tracking multiple targets.IEEE Transactions on Image Processing, 30:1439– 1452, 2020","venue":null,"work_id":"09803a27-d1ac-482e-a09a-91c8fb218b4f","year":2020},"citing_paper":{"arxiv_id":"2505.21943","last_updated":"2025-05-28T03:53:08Z","snapshot_observed_at":"2026-08-16T04:24:31.601514Z","submitted_at":"2025-05-28T03:53:08Z","title":"Point-to-Region Loss for Semi-Supervised Point-Based Crowd Counting","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:02.399641Z"},"links":{"citing_paper":"/paper/2505.21943"},"observation_digest":"sha256:eaff7305c2da0b21fc852eccd2c3b192b15ea7d0b30f02ff6947b620b3f9775d","observation_id":"2976a1db-6423-468a-833a-0e8d0c2e3a14","resolution":{"observed_at":"2026-08-07T13:24:13.715010Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:24:13.252989Z","title":"Crowd counting and indi- vidual localization using pseudo square label.IEEE Access,","venue":null,"work_id":"24bcd7db-664d-4a36-976e-6051f43dcd05","year":null},"citing_paper":{"arxiv_id":"2505.21943","last_updated":"2025-05-28T03:53:08Z","snapshot_observed_at":"2026-08-16T04:24:31.601514Z","submitted_at":"2025-05-28T03:53:08Z","title":"Point-to-Region Loss for Semi-Supervised Point-Based Crowd Counting","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:02.505790Z"},"links":{"citing_paper":"/paper/2505.21943"},"observation_digest":"sha256:8defc5fa79b563d1098a0cbcc4940a63992c3f8313ca58a083fbf522afa41414","observation_id":"2584ba7c-ad40-4101-91be-e29d87a88328","resolution":{"observed_at":"2026-08-07T13:24:13.404585Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:24:02.597856Z","title":"Grad-cam: Visual explanations from deep networks via gradient-based localization","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.21943","last_updated":"2025-05-28T03:53:08Z","snapshot_observed_at":"2026-08-16T04:24:31.601514Z","submitted_at":"2025-05-28T03:53:08Z","title":"Point-to-Region Loss for Semi-Supervised Point-Based Crowd Counting","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:02.597856Z"},"links":{"citing_paper":"/paper/2505.21943"},"observation_digest":"sha256:2bdb90f424f7490e8e9a3228a14ccdf615e257a393124f101b1d78ab9f1fe396","observation_id":"4e12aa9e-01e8-4edb-9daa-966bcbedfb18","resolution":{"observed_at":"2026-08-07T13:24:02.597856Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:24:12.972161Z","title":"Training- free object counting with prompts","venue":null,"work_id":"28764c5e-e4d1-4a15-aad4-99bb56c9b000","year":2024},"citing_paper":{"arxiv_id":"2505.21943","last_updated":"2025-05-28T03:53:08Z","snapshot_observed_at":"2026-08-16T04:24:31.601514Z","submitted_at":"2025-05-28T03:53:08Z","title":"Point-to-Region Loss for Semi-Supervised Point-Based Crowd Counting","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:02.669716Z"},"links":{"citing_paper":"/paper/2505.21943"},"observation_digest":"sha256:32d4613119b17d4362eb4ec3c5f37e4b93f35592a727a6ba31fd171697463145","observation_id":"2dc8a2d1-c6ab-47e8-95d8-26d198ae9bd8","resolution":{"observed_at":"2026-08-07T13:24:13.063815Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:24:12.870171Z","title":"Crowd counting in the frequency domain","venue":null,"work_id":"f5084652-b48a-4bd7-ad64-b2a23ef8016e","year":2022},"citing_paper":{"arxiv_id":"2505.21943","last_updated":"2025-05-28T03:53:08Z","snapshot_observed_at":"2026-08-16T04:24:31.601514Z","submitted_at":"2025-05-28T03:53:08Z","title":"Point-to-Region Loss for Semi-Supervised Point-Based Crowd Counting","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:02.761807Z"},"links":{"citing_paper":"/paper/2505.21943"},"observation_digest":"sha256:4b60991a8cf47fc0a04ae087e24f9db9d72d98e3cdecc0bd260a016d1358c34c","observation_id":"d72d7b8c-0bc0-4188-b049-179ebcee32e4","resolution":{"observed_at":"2026-08-07T13:24:12.908785Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:24:12.704905Z","title":"Crowd counting in the frequency domain","venue":null,"work_id":"2eb9e0f1-9d73-4dda-92ba-7562d95dff21","year":2022},"citing_paper":{"arxiv_id":"2505.21943","last_updated":"2025-05-28T03:53:08Z","snapshot_observed_at":"2026-08-16T04:24:31.601514Z","submitted_at":"2025-05-28T03:53:08Z","title":"Point-to-Region Loss for Semi-Supervised Point-Based Crowd Counting","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:02.860037Z"},"links":{"citing_paper":"/paper/2505.21943"},"observation_digest":"sha256:db3f69f2d2df192f30165992d0720b79cbcc9a0f9ba7e6539ab97a8406779aa6","observation_id":"27eb7e5e-7c11-4727-9b61-09e68fda3028","resolution":{"observed_at":"2026-08-07T13:24:12.777716Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:24:12.548428Z","title":"Generalized char- acteristic function loss for crowd analysis in the frequency domain.IEEE Transactions on Pattern Analysis and Ma- chine Intelligence, 2023","venue":null,"work_id":"141bf4ce-9609-448d-b310-da85f11145d4","year":2023},"citing_paper":{"arxiv_id":"2505.21943","last_updated":"2025-05-28T03:53:08Z","snapshot_observed_at":"2026-08-16T04:24:31.601514Z","submitted_at":"2025-05-28T03:53:08Z","title":"Point-to-Region Loss for Semi-Supervised Point-Based Crowd Counting","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:02.965307Z"},"links":{"citing_paper":"/paper/2505.21943"},"observation_digest":"sha256:c16a841030ea5299f55ffab883b9280bd1dfc7d60fb5895909d224a5fb8b0afe","observation_id":"b0bf71e9-291a-43e0-b7e9-b4c815aa64a9","resolution":{"observed_at":"2026-08-07T13:24:12.634932Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1312.6034","last_updated":"2014-04-19T11:54:52Z","snapshot_observed_at":"2026-08-17T14:45:30.096775Z","submitted_at":"2013-12-20T16:45:54Z","title":"Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1312.6034","snapshot_observed_at":"2026-08-07T13:24:03.059830Z","title":"Deep inside convolutional networks: Visu- alising image classification models and saliency maps.arXiv preprint arXiv:1312.6034, 2013","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2505.21943","last_updated":"2025-05-28T03:53:08Z","snapshot_observed_at":"2026-08-16T04:24:31.601514Z","submitted_at":"2025-05-28T03:53:08Z","title":"Point-to-Region Loss for Semi-Supervised Point-Based Crowd Counting","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:03.059830Z"},"links":{"cited_paper":"/paper/1312.6034","citing_paper":"/paper/2505.21943"},"observation_digest":"sha256:060054094dfcfde7274dddb0919a8e56085cc6a1fba281fe45c28f4fb5e75cef","observation_id":"375ecae0-84e6-4f5c-aa6c-931b41f721a8","resolution":{"observed_at":"2026-08-07T13:24:03.059830Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:24:12.401955Z","title":"Learning to count in the crowd from limited labeled data","venue":null,"work_id":"745c2791-fece-43f6-aa9b-5ab9e4e12a5a","year":2020},"citing_paper":{"arxiv_id":"2505.21943","last_updated":"2025-05-28T03:53:08Z","snapshot_observed_at":"2026-08-16T04:24:31.601514Z","submitted_at":"2025-05-28T03:53:08Z","title":"Point-to-Region Loss for Semi-Supervised Point-Based Crowd Counting","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:03.150639Z"},"links":{"citing_paper":"/paper/2505.21943"},"observation_digest":"sha256:3cfb98eb163cfe9a7ffc755baff5f9fc6efcb5e009b9f21cdbeb8e1b0b8ed656","observation_id":"addfdeee-e5c1-4cfe-9700-a9f4073b7ffc","resolution":{"observed_at":"2026-08-07T13:24:12.474361Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:24:12.197694Z","title":"Jhu-crowd++: Large-scale crowd counting dataset and a benchmark method.IEEE transactions on pattern analysis and machine intelligence, 44(5):2594–2609, 2020","venue":null,"work_id":"514bcb3a-14b6-4693-934a-0a61d31f5703","year":2020},"citing_paper":{"arxiv_id":"2505.21943","last_updated":"2025-05-28T03:53:08Z","snapshot_observed_at":"2026-08-16T04:24:31.601514Z","submitted_at":"2025-05-28T03:53:08Z","title":"Point-to-Region Loss for Semi-Supervised Point-Based Crowd Counting","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:03.253734Z"},"links":{"citing_paper":"/paper/2505.21943"},"observation_digest":"sha256:4c7ed0f8c09b69b09d11db3a769105a131bf06639a8f837b05eee38c670e2d29","observation_id":"9e4b9b3e-4983-4918-9189-22d6e2c099c7","resolution":{"observed_at":"2026-08-07T13:24:12.328856Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:24:11.974953Z","title":"Fixmatch: Simplifying semi-supervised learning with consistency and confidence","venue":null,"work_id":"ce20491e-2448-4376-b94d-690823d70bbc","year":2020},"citing_paper":{"arxiv_id":"2505.21943","last_updated":"2025-05-28T03:53:08Z","snapshot_observed_at":"2026-08-16T04:24:31.601514Z","submitted_at":"2025-05-28T03:53:08Z","title":"Point-to-Region Loss for Semi-Supervised Point-Based Crowd Counting","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:03.370168Z"},"links":{"citing_paper":"/paper/2505.21943"},"observation_digest":"sha256:488e0797cc84954325a957fe05e0c29c425a8e7190863bb7f1ce28f0ceada7e3","observation_id":"63e253f9-2ce9-4e72-8d13-197647a4d22d","resolution":{"observed_at":"2026-08-07T13:24:12.095004Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:24:11.762614Z","title":"Rethinking counting and localization in crowds: A purely point-based framework","venue":null,"work_id":"46d1d30a-130a-481a-94be-c8b26a629720","year":null},"citing_paper":{"arxiv_id":"2505.21943","last_updated":"2025-05-28T03:53:08Z","snapshot_observed_at":"2026-08-16T04:24:31.601514Z","submitted_at":"2025-05-28T03:53:08Z","title":"Point-to-Region Loss for Semi-Supervised Point-Based Crowd Counting","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:03.489807Z"},"links":{"citing_paper":"/paper/2505.21943"},"observation_digest":"sha256:d1e4565260e759783ae29423c803c899bcc719e9af8f25acfb3044cba08e0d6f","observation_id":"74f79154-bed7-44d3-8d70-fc91327315a9","resolution":{"observed_at":"2026-08-07T13:24:11.885822Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:24:11.470328Z","title":"Riedmiller","venue":null,"work_id":"9fcedb4f-0296-46de-860a-4d92a90e107f","year":2015},"citing_paper":{"arxiv_id":"2505.21943","last_updated":"2025-05-28T03:53:08Z","snapshot_observed_at":"2026-08-16T04:24:31.601514Z","submitted_at":"2025-05-28T03:53:08Z","title":"Point-to-Region Loss for Semi-Supervised Point-Based Crowd Counting","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:03.608445Z"},"links":{"citing_paper":"/paper/2505.21943"},"observation_digest":"sha256:42d79d91fd9421830e08351b83d30542929c316792e01755aee443c42fe11925","observation_id":"8ccf5e90-5ec7-4988-8e9d-752d044d7ece","resolution":{"observed_at":"2026-08-07T13:24:11.649668Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:24:11.204533Z","title":"Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results.Advances in neural information processing systems, 30, 2017","venue":null,"work_id":"c44b10e4-778e-4386-895a-9cc77809eef0","year":2017},"citing_paper":{"arxiv_id":"2505.21943","last_updated":"2025-05-28T03:53:08Z","snapshot_observed_at":"2026-08-16T04:24:31.601514Z","submitted_at":"2025-05-28T03:53:08Z","title":"Point-to-Region Loss for Semi-Supervised Point-Based Crowd Counting","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:03.682536Z"},"links":{"citing_paper":"/paper/2505.21943"},"observation_digest":"sha256:6a9ffce7ec2540f703a110cad48ce0091ea0601fe34b9b7b35db86675b5462f7","observation_id":"47b02ab4-d8a9-491f-a8d6-0cfa12030a14","resolution":{"observed_at":"2026-08-07T13:24:11.307081Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:24:11.001181Z","title":"Kernel- based density map generation for dense object counting","venue":null,"work_id":"31135dfb-2855-4ecf-8af1-61218fbf8174","year":2020},"citing_paper":{"arxiv_id":"2505.21943","last_updated":"2025-05-28T03:53:08Z","snapshot_observed_at":"2026-08-16T04:24:31.601514Z","submitted_at":"2025-05-28T03:53:08Z","title":"Point-to-Region Loss for Semi-Supervised Point-Based Crowd Counting","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:03.756530Z"},"links":{"citing_paper":"/paper/2505.21943"},"observation_digest":"sha256:5c445e7cac914430b8ac8f565be59c4aa1e34877ba7f9d205d670e5c62b1a1f6","observation_id":"3430701b-f1aa-4fdc-8e64-8ba5bfdbc240","resolution":{"observed_at":"2026-08-07T13:24:11.099769Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:24:10.798559Z","title":"A generalized loss function for crowd counting and localization","venue":null,"work_id":"6c561ab0-d535-4bbd-bb9c-45a955a99399","year":1974},"citing_paper":{"arxiv_id":"2505.21943","last_updated":"2025-05-28T03:53:08Z","snapshot_observed_at":"2026-08-16T04:24:31.601514Z","submitted_at":"2025-05-28T03:53:08Z","title":"Point-to-Region Loss for Semi-Supervised Point-Based Crowd Counting","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:03.844178Z"},"links":{"citing_paper":"/paper/2505.21943"},"observation_digest":"sha256:f2681efed8a18f8e7d6beb4a4a053aeae6182d2aebcf8e1721200e6c129d8198","observation_id":"7861a3df-aeca-42f8-abed-95da41bba726","resolution":{"observed_at":"2026-08-07T13:24:10.891323Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:24:10.546578Z","title":"Robust zero-shot crowd counting and localization with adaptive res- olution sam","venue":null,"work_id":"dce25136-fc49-462b-82e0-8c8909473248","year":2024},"citing_paper":{"arxiv_id":"2505.21943","last_updated":"2025-05-28T03:53:08Z","snapshot_observed_at":"2026-08-16T04:24:31.601514Z","submitted_at":"2025-05-28T03:53:08Z","title":"Point-to-Region Loss for Semi-Supervised Point-Based Crowd Counting","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:03.902739Z"},"links":{"citing_paper":"/paper/2505.21943"},"observation_digest":"sha256:1e80831a55ec9f6a9cf986265ced24fe35cf2b3acf4704b2493a87922851d8a2","observation_id":"62c1aaa4-e0fb-44a4-a02e-ae545e6ca790","resolution":{"observed_at":"2026-08-07T13:24:10.659047Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:24:10.384805Z","title":"Distribution matching for crowd counting.Ad- vances in neural information processing systems, 33:1595– 1607, 2020","venue":null,"work_id":"dae704e3-3569-416a-bb35-3d2340cba217","year":2020},"citing_paper":{"arxiv_id":"2505.21943","last_updated":"2025-05-28T03:53:08Z","snapshot_observed_at":"2026-08-16T04:24:31.601514Z","submitted_at":"2025-05-28T03:53:08Z","title":"Point-to-Region Loss for Semi-Supervised Point-Based Crowd Counting","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:03.958132Z"},"links":{"citing_paper":"/paper/2505.21943"},"observation_digest":"sha256:3d2682932682fa65839d0512a13dbcdd13d351b1612f6331987b9548e8137af3","observation_id":"09a2a885-c9f8-4d5c-8eee-2a8ec9400058","resolution":{"observed_at":"2026-08-07T13:24:10.454487Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:24:10.217458Z","title":"Score-cam: Score-weighted visual explanations for convolutional neural networks","venue":null,"work_id":"110b90b2-4313-431f-8b97-99690728cdda","year":2020},"citing_paper":{"arxiv_id":"2505.21943","last_updated":"2025-05-28T03:53:08Z","snapshot_observed_at":"2026-08-16T04:24:31.601514Z","submitted_at":"2025-05-28T03:53:08Z","title":"Point-to-Region Loss for Semi-Supervised Point-Based Crowd Counting","version":1},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:04.033948Z"},"links":{"citing_paper":"/paper/2505.21943"},"observation_digest":"sha256:cad49ad14029c70664598c186e15b27d8666f881cbb43849f393e510bbad5ad6","observation_id":"4cfefb73-c01a-422b-ab37-2c0f0b19527f","resolution":{"observed_at":"2026-08-07T13:24:10.307455Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:24:09.990128Z","title":"Learning from synthetic data for crowd counting in the wild","venue":null,"work_id":"700d244e-f2a3-4501-8e47-9f574da4b55b","year":2019},"citing_paper":{"arxiv_id":"2505.21943","last_updated":"2025-05-28T03:53:08Z","snapshot_observed_at":"2026-08-16T04:24:31.601514Z","submitted_at":"2025-05-28T03:53:08Z","title":"Point-to-Region Loss for Semi-Supervised Point-Based Crowd Counting","version":1},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:04.392049Z"},"links":{"citing_paper":"/paper/2505.21943"},"observation_digest":"sha256:88f7d7298d2bdaced38ddcfe8c89c6750ae41643a0943e50c61297f700a57602","observation_id":"dc3c4849-85c0-479b-b061-a8dfc4c44bbe","resolution":{"observed_at":"2026-08-07T13:24:10.107788Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:24:09.768012Z","title":"Nwpu- crowd: A large-scale benchmark for crowd counting and lo- calization.IEEE transactions on pattern analysis and ma- chine intelligence, 43(6):2141–2149, 2020","venue":null,"work_id":"f8d4e9c3-e881-4dc6-aa05-381a935d771a","year":2020},"citing_paper":{"arxiv_id":"2505.21943","last_updated":"2025-05-28T03:53:08Z","snapshot_observed_at":"2026-08-16T04:24:31.601514Z","submitted_at":"2025-05-28T03:53:08Z","title":"Point-to-Region Loss for Semi-Supervised Point-Based Crowd Counting","version":1},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:04.544816Z"},"links":{"citing_paper":"/paper/2505.21943"},"observation_digest":"sha256:4de7d93dc0e3624628afa87da8d2d631a3847f114b81afd1948c992be6a62c33","observation_id":"9a557c0a-c694-4814-8155-45851ee1f379","resolution":{"observed_at":"2026-08-07T13:24:09.869998Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:24:09.572779Z","title":"Density- aware curriculum learning for crowd counting.IEEE Trans- actions on Cybernetics, 52(6):4675–4687, 2020","venue":null,"work_id":"16715150-a2d2-4408-a53f-64302432f88b","year":2020},"citing_paper":{"arxiv_id":"2505.21943","last_updated":"2025-05-28T03:53:08Z","snapshot_observed_at":"2026-08-16T04:24:31.601514Z","submitted_at":"2025-05-28T03:53:08Z","title":"Point-to-Region Loss for Semi-Supervised Point-Based Crowd Counting","version":1},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:04.671264Z"},"links":{"citing_paper":"/paper/2505.21943"},"observation_digest":"sha256:332f1895e7a43f6fc5b6e7afdc4c8d27dec5af63c8e6fa39b33a6505bf67bb1a","observation_id":"ef16ee5d-2fe9-4c79-92e2-976d9a94cabb","resolution":{"observed_at":"2026-08-07T13:24:09.662216Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:24:09.417287Z","title":"Density- aware curriculum learning for crowd counting.IEEE Trans- actions on Cybernetics, 52(6):4675–4687, 2020","venue":null,"work_id":"a662a9d3-e2ba-4b74-86da-c19467833cb7","year":2020},"citing_paper":{"arxiv_id":"2505.21943","last_updated":"2025-05-28T03:53:08Z","snapshot_observed_at":"2026-08-16T04:24:31.601514Z","submitted_at":"2025-05-28T03:53:08Z","title":"Point-to-Region Loss for Semi-Supervised Point-Based Crowd Counting","version":1},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:04.770418Z"},"links":{"citing_paper":"/paper/2505.21943"},"observation_digest":"sha256:8627b6f7869dbe2e42f320931385cad93b1cc0db9b02ae54ae290a3da91351f7","observation_id":"2a6ca7b1-bafe-48ee-ba65-173eb8c8bcfd","resolution":{"observed_at":"2026-08-07T13:24:09.487140Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:24:09.314353Z","title":"Pixel-wise crowd understanding via synthetic data.International Jour- nal of Computer Vision, 129(1):225–245, 2021","venue":null,"work_id":"9fb11ff0-9987-4d1e-a8c9-1bf84e5cca0d","year":2021},"citing_paper":{"arxiv_id":"2505.21943","last_updated":"2025-05-28T03:53:08Z","snapshot_observed_at":"2026-08-16T04:24:31.601514Z","submitted_at":"2025-05-28T03:53:08Z","title":"Point-to-Region Loss for Semi-Supervised Point-Based Crowd Counting","version":1},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:04.863644Z"},"links":{"citing_paper":"/paper/2505.21943"},"observation_digest":"sha256:01181e00612f7ef26611f2931593194e531a9a79bcfee3ae95d7bfbb4a021aee","observation_id":"b9324408-735d-4b1c-8c5e-09f466d2d12f","resolution":{"observed_at":"2026-08-07T13:24:09.360355Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:24:09.206366Z","title":"Dynamic mo- mentum adaptation for zero-shot cross-domain crowd count- ing","venue":null,"work_id":"8c939bd3-5f18-459b-8ad9-398d5c9ec550","year":2021},"citing_paper":{"arxiv_id":"2505.21943","last_updated":"2025-05-28T03:53:08Z","snapshot_observed_at":"2026-08-16T04:24:31.601514Z","submitted_at":"2025-05-28T03:53:08Z","title":"Point-to-Region Loss for Semi-Supervised Point-Based Crowd Counting","version":1},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:04.939054Z"},"links":{"citing_paper":"/paper/2505.21943"},"observation_digest":"sha256:082688fdc8a36d2043ea268aadc55a37e87d350c137ff2945fab6789a5292b94","observation_id":"081e9bc0-c382-4c21-98f9-79cb775aa8da","resolution":{"observed_at":"2026-08-07T13:24:09.268713Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:24:09.070104Z","title":"Zero-shot object counting","venue":null,"work_id":"79c6dbf2-7f6c-4f34-9e5c-40ffc55a8cd9","year":2023},"citing_paper":{"arxiv_id":"2505.21943","last_updated":"2025-05-28T03:53:08Z","snapshot_observed_at":"2026-08-16T04:24:31.601514Z","submitted_at":"2025-05-28T03:53:08Z","title":"Point-to-Region Loss for Semi-Supervised Point-Based Crowd Counting","version":1},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:05.033378Z"},"links":{"citing_paper":"/paper/2505.21943"},"observation_digest":"sha256:4bc00d50cc5b714ff72751bec07d9e6b1f2ae497f3d476494e5be843918ec671","observation_id":"49c7ba1b-533c-411c-9575-fc4c55411436","resolution":{"observed_at":"2026-08-07T13:24:09.121334Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:24:08.954487Z","title":"Cross-view cross-scene multi-view crowd counting","venue":null,"work_id":"209187c6-93ee-4a7a-ac8c-4a3788d3949e","year":2021},"citing_paper":{"arxiv_id":"2505.21943","last_updated":"2025-05-28T03:53:08Z","snapshot_observed_at":"2026-08-16T04:24:31.601514Z","submitted_at":"2025-05-28T03:53:08Z","title":"Point-to-Region Loss for Semi-Supervised Point-Based Crowd Counting","version":1},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:05.140569Z"},"links":{"citing_paper":"/paper/2505.21943"},"observation_digest":"sha256:da558efa7891996d7e6f36f7802ae684f252c359883165e173b64b4ae2989a61","observation_id":"589c601b-fb4f-4bce-a1aa-3ebb24d2f15f","resolution":{"observed_at":"2026-08-07T13:24:09.003969Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:24:08.818905Z","title":"Single-image crowd counting via multi-column convolutional neural network","venue":null,"work_id":"3dbf8f5b-3ae6-478f-90e3-a4ac48346810","year":2016},"citing_paper":{"arxiv_id":"2505.21943","last_updated":"2025-05-28T03:53:08Z","snapshot_observed_at":"2026-08-16T04:24:31.601514Z","submitted_at":"2025-05-28T03:53:08Z","title":"Point-to-Region Loss for Semi-Supervised Point-Based Crowd Counting","version":1},"reference_index":73,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:05.252663Z"},"links":{"citing_paper":"/paper/2505.21943"},"observation_digest":"sha256:89be580702eae4035374548e4d3d58bcc502d3ea968f108a579ee0248f97f143","observation_id":"2af1b831-13a7-4b27-8471-03d9108f50ca","resolution":{"observed_at":"2026-08-07T13:24:08.867720Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:24:08.650950Z","title":null,"venue":null,"work_id":"24657e93-e3a1-417f-86a2-434249977ddd","year":2023},"citing_paper":{"arxiv_id":"2505.21943","last_updated":"2025-05-28T03:53:08Z","snapshot_observed_at":"2026-08-16T04:24:31.601514Z","submitted_at":"2025-05-28T03:53:08Z","title":"Point-to-Region Loss for Semi-Supervised Point-Based Crowd Counting","version":1},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:05.334106Z"},"links":{"citing_paper":"/paper/2505.21943"},"observation_digest":"sha256:54b28fe7ae21ecf78f7acce3dec91f51599596e359dea81084e92dc0e2808832","observation_id":"8114dffc-8aa0-4d06-a28f-0f46601b9b35","resolution":{"observed_at":"2026-08-07T13:24:08.727017Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:24:08.526942Z","title":"Crowd anomaly event de- tection in surveillance video based on the evolution of the spatial position relationship feature","venue":null,"work_id":"060306fa-d7bf-44a9-8b25-95dd3ad4da6d","year":2018},"citing_paper":{"arxiv_id":"2505.21943","last_updated":"2025-05-28T03:53:08Z","snapshot_observed_at":"2026-08-16T04:24:31.601514Z","submitted_at":"2025-05-28T03:53:08Z","title":"Point-to-Region Loss for Semi-Supervised Point-Based Crowd Counting","version":1},"reference_index":75,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:05.449205Z"},"links":{"citing_paper":"/paper/2505.21943"},"observation_digest":"sha256:1f914771951cd6a10963dab11a7b3710a7f1a624883c17073862e9be8b14c126","observation_id":"eb9d1cf0-7fd8-4a85-904d-c59ba5328977","resolution":{"observed_at":"2026-08-07T13:24:08.571310Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:24:08.366852Z","title":"Gradient-based instance-specific visual explanations for ob- ject specification and object discrimination.IEEE Transac- tions on Pattern Analysis and Machine Intelligence, 2024","venue":null,"work_id":"6ea193e4-d7ee-4203-83ce-537f81b0eb34","year":2024},"citing_paper":{"arxiv_id":"2505.21943","last_updated":"2025-05-28T03:53:08Z","snapshot_observed_at":"2026-08-16T04:24:31.601514Z","submitted_at":"2025-05-28T03:53:08Z","title":"Point-to-Region Loss for Semi-Supervised Point-Based Crowd Counting","version":1},"reference_index":76,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:05.517006Z"},"links":{"citing_paper":"/paper/2505.21943"},"observation_digest":"sha256:a05227bac860051f4dee55f10eee03b005a8ee027b819ad631aaf327cddce215","observation_id":"66bdc0cb-4392-4714-bc33-dcef3e8560b6","resolution":{"observed_at":"2026-08-07T13:24:08.442903Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:24:08.247559Z","title":"Gradient-based visual explanation for transformer-based clip","venue":null,"work_id":"ed6b0a3c-012b-4430-b365-5aecc0e03167","year":2024},"citing_paper":{"arxiv_id":"2505.21943","last_updated":"2025-05-28T03:53:08Z","snapshot_observed_at":"2026-08-16T04:24:31.601514Z","submitted_at":"2025-05-28T03:53:08Z","title":"Point-to-Region Loss for Semi-Supervised Point-Based Crowd Counting","version":1},"reference_index":77,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:05.592410Z"},"links":{"citing_paper":"/paper/2505.21943"},"observation_digest":"sha256:05e315d8ffb4d6d6c1bec5f7a396b8784a5603a039f3f1e6b3f35160f37a4747","observation_id":"5eb39c94-c5ec-46c2-99e4-33294907d3fa","resolution":{"observed_at":"2026-08-07T13:24:08.315971Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:24:05.679648Z","title":"Learning deep features for discrimina- tive localization","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.21943","last_updated":"2025-05-28T03:53:08Z","snapshot_observed_at":"2026-08-16T04:24:31.601514Z","submitted_at":"2025-05-28T03:53:08Z","title":"Point-to-Region Loss for Semi-Supervised Point-Based Crowd Counting","version":1},"reference_index":78,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:05.679648Z"},"links":{"citing_paper":"/paper/2505.21943"},"observation_digest":"sha256:128b4ea1b5eebaab82c138ed565960d717791d939bb4dd44883cb80002158c85","observation_id":"0e36ea28-5668-4745-ac27-ee40297d7f26","resolution":{"observed_at":"2026-08-07T13:24:05.679648Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:24:08.073062Z","title":"Fine-grained fragment diffusion for cross domain crowd counting","venue":null,"work_id":"78574606-ae38-481a-9bc6-3e79677c2e60","year":null},"citing_paper":{"arxiv_id":"2505.21943","last_updated":"2025-05-28T03:53:08Z","snapshot_observed_at":"2026-08-16T04:24:31.601514Z","submitted_at":"2025-05-28T03:53:08Z","title":"Point-to-Region Loss for Semi-Supervised Point-Based Crowd Counting","version":1},"reference_index":79,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:05.770867Z"},"links":{"citing_paper":"/paper/2505.21943"},"observation_digest":"sha256:2ca227c447ec14d798fae780c2d2ccc815f0765e7178dde97e12094853b09420","observation_id":"2ee676c8-b3ba-4c22-a8d9-0d9c79742a65","resolution":{"observed_at":"2026-08-07T13:24:08.148695Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:24:07.946147Z","title":"Find gold in sand: Fine-grained similarity min- ing for domain-adaptive crowd counting.IEEE Transactions on Multimedia, 2023","venue":null,"work_id":"7ab0dc9a-3cc2-45a7-a7b2-87d3d65a240c","year":2023},"citing_paper":{"arxiv_id":"2505.21943","last_updated":"2025-05-28T03:53:08Z","snapshot_observed_at":"2026-08-16T04:24:31.601514Z","submitted_at":"2025-05-28T03:53:08Z","title":"Point-to-Region Loss for Semi-Supervised Point-Based Crowd Counting","version":1},"reference_index":80,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:05.860920Z"},"links":{"citing_paper":"/paper/2505.21943"},"observation_digest":"sha256:9333a9cdfaa3da04e49cb6d298d89a88fca3eb91c70a2a241b51889bdb8f1b21","observation_id":"fecbc342-cee6-43bf-9fc5-561c8f5ebc17","resolution":{"observed_at":"2026-08-07T13:24:08.010952Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:24:07.773724Z","title":"1 and Algo","venue":null,"work_id":"89e0216e-fe78-47c7-9f77-a96d0955ac42","year":null},"citing_paper":{"arxiv_id":"2505.21943","last_updated":"2025-05-28T03:53:08Z","snapshot_observed_at":"2026-08-16T04:24:31.601514Z","submitted_at":"2025-05-28T03:53:08Z","title":"Point-to-Region Loss for Semi-Supervised Point-Based Crowd Counting","version":1},"reference_index":81,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:05.936501Z"},"links":{"citing_paper":"/paper/2505.21943"},"observation_digest":"sha256:f0d10142b0ea09692d5041defa9a1a9ee4c342050408da6dc7b23ab78983713a","observation_id":"0bff3fae-00e3-42d8-b256-36459664fcda","resolution":{"observed_at":"2026-08-07T13:24:07.847056Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:24:07.584776Z","title":"For labeled images, we apply horizontal flips to each cropped sample with a probability of 0.5 and randomly resize the images with a scale factor be- tween 0.7 and 1.3","venue":null,"work_id":"03cef84b-8b22-4775-9526-e1c4d108d5d1","year":null},"citing_paper":{"arxiv_id":"2505.21943","last_updated":"2025-05-28T03:53:08Z","snapshot_observed_at":"2026-08-16T04:24:31.601514Z","submitted_at":"2025-05-28T03:53:08Z","title":"Point-to-Region Loss for Semi-Supervised Point-Based Crowd Counting","version":1},"reference_index":82,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:06.017301Z"},"links":{"citing_paper":"/paper/2505.21943"},"observation_digest":"sha256:793a4b0e609d5d638d9843a544c8195f2a50d41d80bc3a82bcb53741cdd58c3b","observation_id":"56410653-20c7-4a4e-b692-88ff9c2d3a30","resolution":{"observed_at":"2026-08-07T13:24:07.673453Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:24:07.373953Z","title":"We present the empirical results in Table 3 to demonstrate its advantage","venue":null,"work_id":"27a0e0ea-de27-4a4f-90ac-94e821115423","year":null},"citing_paper":{"arxiv_id":"2505.21943","last_updated":"2025-05-28T03:53:08Z","snapshot_observed_at":"2026-08-16T04:24:31.601514Z","submitted_at":"2025-05-28T03:53:08Z","title":"Point-to-Region Loss for Semi-Supervised Point-Based Crowd Counting","version":1},"reference_index":83,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:06.111291Z"},"links":{"citing_paper":"/paper/2505.21943"},"observation_digest":"sha256:8a2cd866e11bc2feee1c7bdb676a6fc797ebd6db59977383f22896eebca44d23","observation_id":"3558320e-2510-4b21-9dd0-e60653c8c92a","resolution":{"observed_at":"2026-08-07T13:24:07.482057Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:24:07.175894Z","title":"Comparison of counting losses (100% Label Pct.) since the second term for the background part is set to 0, as shown in (9)","venue":null,"work_id":"00eafd76-f867-4530-b986-b5cd7e1fe812","year":null},"citing_paper":{"arxiv_id":"2505.21943","last_updated":"2025-05-28T03:53:08Z","snapshot_observed_at":"2026-08-16T04:24:31.601514Z","submitted_at":"2025-05-28T03:53:08Z","title":"Point-to-Region Loss for Semi-Supervised Point-Based Crowd Counting","version":1},"reference_index":84,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:06.200623Z"},"links":{"citing_paper":"/paper/2505.21943"},"observation_digest":"sha256:706373d36a06d0c8029ddd08f4622c5b1d538c6a56d6ec0df49f7ca63e54a4ff","observation_id":"e7e934c1-2436-44a6-a031-9cf04e3770bc","resolution":{"observed_at":"2026-08-07T13:24:07.267669Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:24:06.966632Z","title":"2:Related Works","venue":null,"work_id":"016c5a73-d3ee-4ae0-acaf-b8d0599a9039","year":null},"citing_paper":{"arxiv_id":"2505.21943","last_updated":"2025-05-28T03:53:08Z","snapshot_observed_at":"2026-08-16T04:24:31.601514Z","submitted_at":"2025-05-28T03:53:08Z","title":"Point-to-Region Loss for Semi-Supervised Point-Based Crowd Counting","version":1},"reference_index":85,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:06.256811Z"},"links":{"citing_paper":"/paper/2505.21943"},"observation_digest":"sha256:19884a76931755f45b7558836ba0962f9434e3a3be1e89d03420572ac78dabd7","observation_id":"d8dc1f0b-140b-4f9b-a2f2-baef22784cb8","resolution":{"observed_at":"2026-08-07T13:24:07.060783Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:24:06.808461Z","title":"Pseudo-Labels In Fig","venue":null,"work_id":"506dd345-a60b-4acf-b32a-07bac43c898b","year":null},"citing_paper":{"arxiv_id":"2505.21943","last_updated":"2025-05-28T03:53:08Z","snapshot_observed_at":"2026-08-16T04:24:31.601514Z","submitted_at":"2025-05-28T03:53:08Z","title":"Point-to-Region Loss for Semi-Supervised Point-Based Crowd Counting","version":1},"reference_index":86,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:06.333781Z"},"links":{"citing_paper":"/paper/2505.21943"},"observation_digest":"sha256:330a0211f570ffd5be7643920721638e7d5bb82540286e9c9debaddab4bbe342","observation_id":"b49ffb20-16b1-4512-9edb-5e2b05968a3b","resolution":{"observed_at":"2026-08-07T13:24:06.879757Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2505.21943","last_updated":"2025-05-28T03:53:08Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-16T04:24:31.601514Z","submitted_at":"2025-05-28T03:53:08Z","title":"Point-to-Region Loss for Semi-Supervised Point-Based Crowd Counting"},"reference_resolution":{"displayed":86,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":10,"verified_exact":2,"verified_fuzzy":74},"total_outbound_references":86},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"thesis":"As of 19 August 2026, this Paper Citation Record lists 86 of 86 outbound references and 0 inbound Pith citation observations for arXiv:2505.21943."}