{"as_of":"2026-08-16T15:13:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:42893706394fa920d58ae0349eabc9a831db3f80367a99d406698e7e39929207","coverage":[{"denominator":41,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":41,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-15T22:55:38.635413Z","state":"measured"},{"denominator":41,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":41,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-16T06:30:59.297886+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/2505.05943/citation-record","integrity":"/paper/2505.05943/integrity","json":"/paper/2505.05943/citation-record.json","paper":"/paper/2505.05943"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:55:38.463893Z","title":"Gradient-based learning applied to document recognition,","venue":null,"work_id":null,"year":1998},"citing_paper":{"arxiv_id":"2505.05943","last_updated":"2025-05-09T10:36:30Z","snapshot_observed_at":"2026-08-16T14:49:47.657763Z","submitted_at":"2025-05-09T10:36:30Z","title":"Achieving 3D Attention via Triplet Squeeze and Excitation Block","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-15T22:55:38.463893Z"},"links":{"citing_paper":"/paper/2505.05943"},"observation_digest":"sha256:c71a3d03811059b1801bcb2b4d03b3933a3d150f7309a3a6e2b3b1be8641d31d","observation_id":"a86d5b6d-220c-4859-bdf2-0e1d5b35d68f","resolution":{"observed_at":"2026-08-15T22:55:38.463893Z","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":"2026-08-15T22:55:38.469109Z","title":"Imagenet classifica- tion with deep convolutional neural networks,","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2505.05943","last_updated":"2025-05-09T10:36:30Z","snapshot_observed_at":"2026-08-16T14:49:47.657763Z","submitted_at":"2025-05-09T10:36:30Z","title":"Achieving 3D Attention via Triplet Squeeze and Excitation Block","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-15T22:55:38.469109Z"},"links":{"citing_paper":"/paper/2505.05943"},"observation_digest":"sha256:e2e23005422cdd2af4ba59a0637847835f35346533fadeaad085613dbe966008","observation_id":"2b500c85-528e-4c40-bfe4-20a2bc9cd31a","resolution":{"observed_at":"2026-08-15T22:55:38.469109Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1409.4842","last_updated":"2014-09-17T01:03:11Z","snapshot_observed_at":"2026-08-14T23:19:12.989484Z","submitted_at":"2014-09-17T01:03:11Z","title":"Going Deeper with Convolutions","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1409.4842","snapshot_observed_at":"2026-08-15T22:55:38.474209Z","title":"Going deeper with convolutions,","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2505.05943","last_updated":"2025-05-09T10:36:30Z","snapshot_observed_at":"2026-08-16T14:49:47.657763Z","submitted_at":"2025-05-09T10:36:30Z","title":"Achieving 3D Attention via Triplet Squeeze and Excitation Block","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-15T22:55:38.474209Z"},"links":{"cited_paper":"/paper/1409.4842","citing_paper":"/paper/2505.05943"},"observation_digest":"sha256:bcc9deee6eed7ccea18bd1d5bb1d5e852e1927be72a6051a33dd659dca04a7d8","observation_id":"de8679f5-4532-4d34-8bd5-2dffff4d81c6","resolution":{"observed_at":"2026-08-15T22:55:38.474209Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1409.1556","last_updated":"2015-04-10T16:25:04Z","snapshot_observed_at":"2026-08-14T23:20:42.336514Z","submitted_at":"2014-09-04T19:48:04Z","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1409.1556","snapshot_observed_at":"2026-08-15T22:55:38.479357Z","title":"Very deep convolutional networks for large-scale image recognition,","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2505.05943","last_updated":"2025-05-09T10:36:30Z","snapshot_observed_at":"2026-08-16T14:49:47.657763Z","submitted_at":"2025-05-09T10:36:30Z","title":"Achieving 3D Attention via Triplet Squeeze and Excitation Block","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-15T22:55:38.479357Z"},"links":{"cited_paper":"/paper/1409.1556","citing_paper":"/paper/2505.05943"},"observation_digest":"sha256:ccf05bf96807f1c83d554ffead1d0c972c06aaf4d9800fb81525f9628253ea6a","observation_id":"bb27c83a-b216-46ab-badf-e5358bd1162b","resolution":{"observed_at":"2026-08-15T22:55:38.479357Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1512.03385","last_updated":"2015-12-10T19:51:55Z","snapshot_observed_at":"2026-07-06T04:39:28.429064Z","submitted_at":"2015-12-10T19:51:55Z","title":"Deep Residual Learning for Image Recognition","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1512.03385","snapshot_observed_at":"2026-08-15T22:55:38.484398Z","title":"Deep residual learning for image recognition,","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2505.05943","last_updated":"2025-05-09T10:36:30Z","snapshot_observed_at":"2026-08-16T14:49:47.657763Z","submitted_at":"2025-05-09T10:36:30Z","title":"Achieving 3D Attention via Triplet Squeeze and Excitation Block","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-15T22:55:38.484398Z"},"links":{"cited_paper":"/paper/1512.03385","citing_paper":"/paper/2505.05943"},"observation_digest":"sha256:fafb54b15fd6e0b9dfe207dedb5eac9bf69d7a528f8cd16ed69ca326623fed98","observation_id":"31f863de-26a4-4862-8ffd-2e11c54738bb","resolution":{"observed_at":"2026-08-15T22:55:38.484398Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1801.04381","last_updated":"2019-03-21T19:44:34Z","snapshot_observed_at":"2026-08-14T19:55:28.045143Z","submitted_at":"2018-01-13T04:46:26Z","title":"MobileNetV2: Inverted Residuals and Linear Bottlenecks","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1801.04381","snapshot_observed_at":"2026-08-15T22:55:38.489102Z","title":"Mobilenetv2: Inverted residuals and linear bottlenecks,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2505.05943","last_updated":"2025-05-09T10:36:30Z","snapshot_observed_at":"2026-08-16T14:49:47.657763Z","submitted_at":"2025-05-09T10:36:30Z","title":"Achieving 3D Attention via Triplet Squeeze and Excitation Block","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-15T22:55:38.489102Z"},"links":{"cited_paper":"/paper/1801.04381","citing_paper":"/paper/2505.05943"},"observation_digest":"sha256:b606fc27335687eefbb4ce0d1e8e89c91ab46f6d2cf92a234fe3605d31d62509","observation_id":"dc57b220-f848-4f76-922c-5308cc211e56","resolution":{"observed_at":"2026-08-15T22:55:38.489102Z","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":"2026-08-15T22:55:39.290518Z","title":"Facial expression and attributes recognition based on multi-task learning of lightweight neural networks,","venue":null,"work_id":"9bc99c81-628d-47a3-9f85-8b1abd994c33","year":2021},"citing_paper":{"arxiv_id":"2505.05943","last_updated":"2025-05-09T10:36:30Z","snapshot_observed_at":"2026-08-16T14:49:47.657763Z","submitted_at":"2025-05-09T10:36:30Z","title":"Achieving 3D Attention via Triplet Squeeze and Excitation Block","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-15T22:55:38.496228Z"},"links":{"citing_paper":"/paper/2505.05943"},"observation_digest":"sha256:2411df2bca66d85025eddc86107d3cfb43b3842ec3cd2d9025ff7ad71a14222c","observation_id":"e4ee95dc-f7e4-4a09-b526-0614ae429ce9","resolution":{"observed_at":"2026-08-15T22:55:39.296387Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1608.06993","last_updated":"2018-01-28T17:12:02Z","snapshot_observed_at":"2026-08-14T21:42:53.838437Z","submitted_at":"2016-08-25T00:44:55Z","title":"Densely Connected Convolutional Networks","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1608.06993","snapshot_observed_at":"2026-08-15T22:55:38.500569Z","title":"Densely connected convolutional networks,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2505.05943","last_updated":"2025-05-09T10:36:30Z","snapshot_observed_at":"2026-08-16T14:49:47.657763Z","submitted_at":"2025-05-09T10:36:30Z","title":"Achieving 3D Attention via Triplet Squeeze and Excitation Block","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-15T22:55:38.500569Z"},"links":{"cited_paper":"/paper/1608.06993","citing_paper":"/paper/2505.05943"},"observation_digest":"sha256:8dfad7b7b7ff7185530b7eaeabd0fa0578854fd62e5618d53df59505358f5216","observation_id":"f491b6e6-bf63-48f4-8759-ada9dfdf0fc5","resolution":{"observed_at":"2026-08-15T22:55:38.500569Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1709.01507","last_updated":"2019-05-16T05:32:17Z","snapshot_observed_at":"2026-08-14T20:35:56.526796Z","submitted_at":"2017-09-05T17:42:13Z","title":"Squeeze-and-Excitation Networks","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1709.01507","snapshot_observed_at":"2026-08-15T22:55:38.506823Z","title":"Squeeze-and-excitation networks,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2505.05943","last_updated":"2025-05-09T10:36:30Z","snapshot_observed_at":"2026-08-16T14:49:47.657763Z","submitted_at":"2025-05-09T10:36:30Z","title":"Achieving 3D Attention via Triplet Squeeze and Excitation Block","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-15T22:55:38.506823Z"},"links":{"cited_paper":"/paper/1709.01507","citing_paper":"/paper/2505.05943"},"observation_digest":"sha256:18a2d2198f806e944b3af32a2f214abe0c545808969c18c7b8918699e182f130","observation_id":"47609838-7f24-4fd0-b200-59b307f2635f","resolution":{"observed_at":"2026-08-15T22:55:38.506823Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1807.06521","last_updated":"2018-07-18T11:20:08Z","snapshot_observed_at":"2026-08-16T02:58:02.665829Z","submitted_at":"2018-07-17T16:05:59Z","title":"CBAM: Convolutional Block Attention Module","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1807.06521","snapshot_observed_at":"2026-08-15T22:55:38.511013Z","title":"Cbam: Convolutional block attention module,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2505.05943","last_updated":"2025-05-09T10:36:30Z","snapshot_observed_at":"2026-08-16T14:49:47.657763Z","submitted_at":"2025-05-09T10:36:30Z","title":"Achieving 3D Attention via Triplet Squeeze and Excitation Block","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-15T22:55:38.511013Z"},"links":{"cited_paper":"/paper/1807.06521","citing_paper":"/paper/2505.05943"},"observation_digest":"sha256:65aeafdec86f903c351da16170f13d053e8f61f69f1e3f17910d32a84762f096","observation_id":"3f8b9ac6-50d7-4430-b0b4-b059903e39c3","resolution":{"observed_at":"2026-08-15T22:55:38.511013Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1807.06514","last_updated":"2018-07-18T11:17:12Z","snapshot_observed_at":"2026-08-16T02:59:40.344650Z","submitted_at":"2018-07-17T15:55:31Z","title":"BAM: Bottleneck Attention Module","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1807.06514","snapshot_observed_at":"2026-08-15T22:55:38.515572Z","title":"Bam: Bottleneck attention module,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2505.05943","last_updated":"2025-05-09T10:36:30Z","snapshot_observed_at":"2026-08-16T14:49:47.657763Z","submitted_at":"2025-05-09T10:36:30Z","title":"Achieving 3D Attention via Triplet Squeeze and Excitation Block","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-15T22:55:38.515572Z"},"links":{"cited_paper":"/paper/1807.06514","citing_paper":"/paper/2505.05943"},"observation_digest":"sha256:01b4ba2c475e1318a36ef825b6efac61900b8c8f3f8f030d04c549d9ecf078d1","observation_id":"8198e05c-b7e8-4c5b-b0a7-a54cdb29037b","resolution":{"observed_at":"2026-08-15T22:55:38.515572Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2010.03045","last_updated":"2020-11-05T19:08:52Z","snapshot_observed_at":"2026-08-11T03:08:55.189310Z","submitted_at":"2020-10-06T21:31:00Z","title":"Rotate to Attend: Convolutional Triplet Attention Module","version":2},"cited_work":{"arxiv_id":"2010.03045","doi":null,"metadata_source":"pith","pith_arxiv_id":"2010.03045","snapshot_observed_at":"2026-08-15T22:55:38.864504Z","title":"Rotate to Attend: Convolutional Triplet Attention Module","venue":"cs.CV","work_id":"85d46b59-7ce0-4bdc-900d-59b471288b11","year":2020},"citing_paper":{"arxiv_id":"2505.05943","last_updated":"2025-05-09T10:36:30Z","snapshot_observed_at":"2026-08-16T14:49:47.657763Z","submitted_at":"2025-05-09T10:36:30Z","title":"Achieving 3D Attention via Triplet Squeeze and Excitation Block","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-15T22:55:38.519770Z"},"links":{"cited_paper":"/paper/2010.03045","citing_paper":"/paper/2505.05943"},"observation_digest":"sha256:e0dfff9777c113b0f71396f55c37901e20cdcacbe0ad6ef992cce13d215f9b7e","observation_id":"9ce73195-0164-4e16-8fb8-db01de217743","resolution":{"observed_at":"2026-08-15T22:55:38.869964Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1706.03762","last_updated":"2023-08-02T00:41:18Z","snapshot_observed_at":"2026-08-16T05:25:19.960199Z","submitted_at":"2017-06-12T17:57:34Z","title":"Attention Is All You Need","version":7},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1706.03762","snapshot_observed_at":"2026-08-15T22:55:38.524264Z","title":"Attention is all you need,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2505.05943","last_updated":"2025-05-09T10:36:30Z","snapshot_observed_at":"2026-08-16T14:49:47.657763Z","submitted_at":"2025-05-09T10:36:30Z","title":"Achieving 3D Attention via Triplet Squeeze and Excitation Block","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-15T22:55:38.524264Z"},"links":{"cited_paper":"/paper/1706.03762","citing_paper":"/paper/2505.05943"},"observation_digest":"sha256:aada3f3afd1835125867d3a06dcae7dfdc7413a9dddf8d8fe4ab4675c8793886","observation_id":"3d5588f5-e190-42b4-852a-b7aac6871968","resolution":{"observed_at":"2026-08-15T22:55:38.524264Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2010.11929","last_updated":"2021-06-03T13:08:56Z","snapshot_observed_at":"2026-08-16T09:25:53.087782Z","submitted_at":"2020-10-22T17:55:59Z","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2010.11929","snapshot_observed_at":"2026-08-15T22:55:38.528288Z","title":"An image is worth 16x16 words: Transformers for image recognition at scale,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2505.05943","last_updated":"2025-05-09T10:36:30Z","snapshot_observed_at":"2026-08-16T14:49:47.657763Z","submitted_at":"2025-05-09T10:36:30Z","title":"Achieving 3D Attention via Triplet Squeeze and Excitation Block","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-15T22:55:38.528288Z"},"links":{"cited_paper":"/paper/2010.11929","citing_paper":"/paper/2505.05943"},"observation_digest":"sha256:027fce5e97ee2fa5e5aa93da724174ed751e6704268d4b22f836d8c648aacb78","observation_id":"9acab24b-ecf0-4f8b-a2e4-5c1cb998e738","resolution":{"observed_at":"2026-08-15T22:55:38.528288Z","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":"2026-08-15T22:55:39.270420Z","title":"Training data-efficient image transformers & distillation through attention,","venue":null,"work_id":"a7cb807a-7099-4508-bc03-fe6f28a817da","year":2021},"citing_paper":{"arxiv_id":"2505.05943","last_updated":"2025-05-09T10:36:30Z","snapshot_observed_at":"2026-08-16T14:49:47.657763Z","submitted_at":"2025-05-09T10:36:30Z","title":"Achieving 3D Attention via Triplet Squeeze and Excitation Block","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-15T22:55:38.532097Z"},"links":{"citing_paper":"/paper/2505.05943"},"observation_digest":"sha256:e6b5e4650b14f14d0680de7df6fccb5dd92ffb3347702f7f64da92203292e774","observation_id":"3ab70881-4466-4452-a72d-1323c9fd91b2","resolution":{"observed_at":"2026-08-15T22:55:39.275205Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T22:55:39.254164Z","title":"A convnet for the 2020s,","venue":null,"work_id":"3ffad70e-146c-4932-80d4-623abba1ca7e","year":2022},"citing_paper":{"arxiv_id":"2505.05943","last_updated":"2025-05-09T10:36:30Z","snapshot_observed_at":"2026-08-16T14:49:47.657763Z","submitted_at":"2025-05-09T10:36:30Z","title":"Achieving 3D Attention via Triplet Squeeze and Excitation Block","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-15T22:55:38.535904Z"},"links":{"citing_paper":"/paper/2505.05943"},"observation_digest":"sha256:0922854a3cf437d2aca5b94b53d78b5c205f25250433d78e9fd610eec6a548a9","observation_id":"582ebbd3-bcc6-4800-81ac-7f777e329bb4","resolution":{"observed_at":"2026-08-15T22:55:39.259313Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T22:55:39.238889Z","title":"Emonext: an adapted convnext for facial emotion recognition,","venue":null,"work_id":"abee1951-9ad0-4283-9ae4-70ee2821ee68","year":2023},"citing_paper":{"arxiv_id":"2505.05943","last_updated":"2025-05-09T10:36:30Z","snapshot_observed_at":"2026-08-16T14:49:47.657763Z","submitted_at":"2025-05-09T10:36:30Z","title":"Achieving 3D Attention via Triplet Squeeze and Excitation Block","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-15T22:55:38.539523Z"},"links":{"citing_paper":"/paper/2505.05943"},"observation_digest":"sha256:d46d630e503cab0379c2db097cb785bc023af1adcac08ce385b86700cd8b1964","observation_id":"2b9aaf86-30ad-4017-88f5-a470ff32d5be","resolution":{"observed_at":"2026-08-15T22:55:39.243867Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1506.02025","last_updated":"2016-02-04T18:08:46Z","snapshot_observed_at":"2026-08-15T13:44:02.183786Z","submitted_at":"2015-06-05T19:54:26Z","title":"Spatial Transformer Networks","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1506.02025","snapshot_observed_at":"2026-08-15T22:55:38.543578Z","title":"Spatial transformer networks,","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2505.05943","last_updated":"2025-05-09T10:36:30Z","snapshot_observed_at":"2026-08-16T14:49:47.657763Z","submitted_at":"2025-05-09T10:36:30Z","title":"Achieving 3D Attention via Triplet Squeeze and Excitation Block","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-15T22:55:38.543578Z"},"links":{"cited_paper":"/paper/1506.02025","citing_paper":"/paper/2505.05943"},"observation_digest":"sha256:40c8aeed9b79223031f6a2c73af2ba9a67d8ae7296aea72769730304ec3ff96c","observation_id":"cb01d91b-4618-4ffc-81c9-58841e955432","resolution":{"observed_at":"2026-08-15T22:55:38.543578Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1904.02874","last_updated":"2021-07-12T12:03:52Z","snapshot_observed_at":"2026-08-14T16:51:22.882986Z","submitted_at":"2019-04-05T05:26:59Z","title":"An Attentive Survey of Attention Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1904.02874","snapshot_observed_at":"2026-08-15T22:55:38.547747Z","title":"An attentive survey of attention models,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2505.05943","last_updated":"2025-05-09T10:36:30Z","snapshot_observed_at":"2026-08-16T14:49:47.657763Z","submitted_at":"2025-05-09T10:36:30Z","title":"Achieving 3D Attention via Triplet Squeeze and Excitation Block","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-15T22:55:38.547747Z"},"links":{"cited_paper":"/paper/1904.02874","citing_paper":"/paper/2505.05943"},"observation_digest":"sha256:4f3e12d524443e77fece81ba5d1e93e778bae33db642de7871568ac61a7fbeb0","observation_id":"649a43f4-dabc-4f7c-845c-8d844175a2f8","resolution":{"observed_at":"2026-08-15T22:55:38.547747Z","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":"2026-08-15T22:55:39.223806Z","title":"Attention mechanisms in computer vision: A survey,","venue":null,"work_id":"97cfb872-caae-44b6-b5ce-ad564dfc19e3","year":2022},"citing_paper":{"arxiv_id":"2505.05943","last_updated":"2025-05-09T10:36:30Z","snapshot_observed_at":"2026-08-16T14:49:47.657763Z","submitted_at":"2025-05-09T10:36:30Z","title":"Achieving 3D Attention via Triplet Squeeze and Excitation Block","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-15T22:55:38.551929Z"},"links":{"citing_paper":"/paper/2505.05943"},"observation_digest":"sha256:f98e5cc25093184b899b2fa7bed0f82c0232c589fee3fc8efc40ff0dc2e0f967","observation_id":"3fa5d850-5994-4714-b30c-61c7740f1a6f","resolution":{"observed_at":"2026-08-15T22:55:39.228199Z","resolver_source":"raw_fallback","status":"malformed_identifier"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1811.12006","last_updated":"2018-11-30T02:55:13Z","snapshot_observed_at":"2026-08-14T17:51:32.516108Z","submitted_at":"2018-11-29T08:15:39Z","title":"Global Second-order Pooling Convolutional Networks","version":2},"cited_work":{"arxiv_id":"1811.12006","doi":null,"metadata_source":"pith","pith_arxiv_id":"1811.12006","snapshot_observed_at":"2026-08-15T22:55:38.788600Z","title":"Global Second-order Pooling Convolutional Networks","venue":"cs.CV","work_id":"706d59b9-1134-42f7-bd08-de2db4487c16","year":2018},"citing_paper":{"arxiv_id":"2505.05943","last_updated":"2025-05-09T10:36:30Z","snapshot_observed_at":"2026-08-16T14:49:47.657763Z","submitted_at":"2025-05-09T10:36:30Z","title":"Achieving 3D Attention via Triplet Squeeze and Excitation Block","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-15T22:55:38.556587Z"},"links":{"cited_paper":"/paper/1811.12006","citing_paper":"/paper/2505.05943"},"observation_digest":"sha256:6e14b6ff12b314446311a3bf700bfabb9e0882ef3c648f7c85df51336eef8b35","observation_id":"e3d7e31e-5dc7-4567-a52b-bd5b922a3673","resolution":{"observed_at":"2026-08-15T22:55:38.793628Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1903.10829","last_updated":"2019-03-26T12:23:52Z","snapshot_observed_at":"2026-08-14T16:56:40.600997Z","submitted_at":"2019-03-26T12:23:52Z","title":"SRM : A Style-based Recalibration Module for Convolutional Neural Networks","version":1},"cited_work":{"arxiv_id":"1903.10829","doi":null,"metadata_source":"pith","pith_arxiv_id":"1903.10829","snapshot_observed_at":"2026-08-15T22:55:38.769885Z","title":"SRM : A Style-based Recalibration Module for Convolutional Neural Networks","venue":"cs.CV","work_id":"2305cb32-43f5-4a2f-89b4-a071b8782e83","year":2019},"citing_paper":{"arxiv_id":"2505.05943","last_updated":"2025-05-09T10:36:30Z","snapshot_observed_at":"2026-08-16T14:49:47.657763Z","submitted_at":"2025-05-09T10:36:30Z","title":"Achieving 3D Attention via Triplet Squeeze and Excitation Block","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-15T22:55:38.560784Z"},"links":{"cited_paper":"/paper/1903.10829","citing_paper":"/paper/2505.05943"},"observation_digest":"sha256:96ffa30df239eb067aa770dd09a56cb99b568b0be4a433c3da5b8b3acd8bfa65","observation_id":"b90185a5-b6dd-44bf-a4b1-2614a793a282","resolution":{"observed_at":"2026-08-15T22:55:38.774773Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1909.11519","last_updated":"2020-03-27T10:08:39Z","snapshot_observed_at":"2026-07-06T08:24:29.472112Z","submitted_at":"2019-09-25T14:26:32Z","title":"Gated Channel Transformation for Visual Recognition","version":2},"cited_work":{"arxiv_id":"1909.11519","doi":null,"metadata_source":"pith","pith_arxiv_id":"1909.11519","snapshot_observed_at":"2026-08-15T22:55:38.751253Z","title":"Gated Channel Transformation for Visual Recognition","venue":"cs.CV","work_id":"360245f4-5edf-4332-9678-197d0302479d","year":2019},"citing_paper":{"arxiv_id":"2505.05943","last_updated":"2025-05-09T10:36:30Z","snapshot_observed_at":"2026-08-16T14:49:47.657763Z","submitted_at":"2025-05-09T10:36:30Z","title":"Achieving 3D Attention via Triplet Squeeze and Excitation Block","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-15T22:55:38.565046Z"},"links":{"cited_paper":"/paper/1909.11519","citing_paper":"/paper/2505.05943"},"observation_digest":"sha256:af5357fff99092d98f692a51eafddae10576895387ecfb30d7f7aa79418a86b1","observation_id":"311a89e8-1e33-4233-94bc-ac826032a2e5","resolution":{"observed_at":"2026-08-15T22:55:38.756039Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T22:55:39.209271Z","title":"Eca-net: Efficient channel attention for deep convolutional neural networks,","venue":null,"work_id":"5a7edd12-923b-4a06-9523-acb3f06bcd1d","year":null},"citing_paper":{"arxiv_id":"2505.05943","last_updated":"2025-05-09T10:36:30Z","snapshot_observed_at":"2026-08-16T14:49:47.657763Z","submitted_at":"2025-05-09T10:36:30Z","title":"Achieving 3D Attention via Triplet Squeeze and Excitation Block","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-15T22:55:38.569251Z"},"links":{"citing_paper":"/paper/2505.05943"},"observation_digest":"sha256:acc65d115e3b1a26d31f50f96210047e864cdba98526204fdf43c9291617b9b6","observation_id":"e2ae2953-18bf-4fb4-a734-ec432b615f24","resolution":{"observed_at":"2026-08-15T22:55:39.213817Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2012.11879","last_updated":"2021-07-23T07:03:52Z","snapshot_observed_at":"2026-08-13T20:41:54.700389Z","submitted_at":"2020-12-22T08:33:27Z","title":"FcaNet: Frequency Channel Attention Networks","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2012.11879","snapshot_observed_at":"2026-08-15T22:55:38.577347Z","title":"Fcanet: Frequency channel attention networks,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2505.05943","last_updated":"2025-05-09T10:36:30Z","snapshot_observed_at":"2026-08-16T14:49:47.657763Z","submitted_at":"2025-05-09T10:36:30Z","title":"Achieving 3D Attention via Triplet Squeeze and Excitation Block","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-15T22:55:38.577347Z"},"links":{"cited_paper":"/paper/2012.11879","citing_paper":"/paper/2505.05943"},"observation_digest":"sha256:597465f424292ee80f830666c6a30a18d9b2716e751bd320ea618ebaf0bd1a93","observation_id":"2645ffe9-9c71-4da3-a189-5837b68c381a","resolution":{"observed_at":"2026-08-15T22:55:38.577347Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1406.6247","last_updated":"2014-06-24T14:16:56Z","snapshot_observed_at":"2026-08-14T23:29:15.291538Z","submitted_at":"2014-06-24T14:16:56Z","title":"Recurrent Models of Visual Attention","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1406.6247","snapshot_observed_at":"2026-08-15T22:55:38.581154Z","title":"Recurrent models of visual attention,","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2505.05943","last_updated":"2025-05-09T10:36:30Z","snapshot_observed_at":"2026-08-16T14:49:47.657763Z","submitted_at":"2025-05-09T10:36:30Z","title":"Achieving 3D Attention via Triplet Squeeze and Excitation Block","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-15T22:55:38.581154Z"},"links":{"cited_paper":"/paper/1406.6247","citing_paper":"/paper/2505.05943"},"observation_digest":"sha256:a59e74992bdbc44ef5d504521d8e4f04526b728a43cf12a42321d607e8ec7d1b","observation_id":"3f47f421-10f7-44cf-a215-42044683259a","resolution":{"observed_at":"2026-08-15T22:55:38.581154Z","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":"2026-08-15T22:55:39.195705Z","title":"Show, attend and tell: Neural image caption generation with visual attention,","venue":null,"work_id":"d5a12b7c-9d96-4fd3-b801-18d696403109","year":2015},"citing_paper":{"arxiv_id":"2505.05943","last_updated":"2025-05-09T10:36:30Z","snapshot_observed_at":"2026-08-16T14:49:47.657763Z","submitted_at":"2025-05-09T10:36:30Z","title":"Achieving 3D Attention via Triplet Squeeze and Excitation Block","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-15T22:55:38.585156Z"},"links":{"citing_paper":"/paper/2505.05943"},"observation_digest":"sha256:359c9d307d8d43d13e444b3bc93fb95363c603e0ad03ca4459151c5e708242c9","observation_id":"a9d1388c-8b06-4469-82c6-18b34fa34128","resolution":{"observed_at":"2026-08-15T22:55:39.199833Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1711.07971","last_updated":"2018-04-13T06:40:44Z","snapshot_observed_at":"2026-08-14T20:11:21.532523Z","submitted_at":"2017-11-21T18:51:16Z","title":"Non-local Neural Networks","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1711.07971","snapshot_observed_at":"2026-08-15T22:55:38.588989Z","title":"Non-local neural networks,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2505.05943","last_updated":"2025-05-09T10:36:30Z","snapshot_observed_at":"2026-08-16T14:49:47.657763Z","submitted_at":"2025-05-09T10:36:30Z","title":"Achieving 3D Attention via Triplet Squeeze and Excitation Block","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-15T22:55:38.588989Z"},"links":{"cited_paper":"/paper/1711.07971","citing_paper":"/paper/2505.05943"},"observation_digest":"sha256:bdd4ab21010e6d740f720c730f6130be7a53f87ccc0ecd7aab4d1e698d45e7c1","observation_id":"52a97831-e80d-4782-a092-9aeb032244fa","resolution":{"observed_at":"2026-08-15T22:55:38.588989Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1704.06904","last_updated":"2017-04-23T10:03:49Z","snapshot_observed_at":"2026-08-14T21:05:21.832997Z","submitted_at":"2017-04-23T10:03:49Z","title":"Residual Attention Network for Image Classification","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1704.06904","snapshot_observed_at":"2026-08-15T22:55:38.592817Z","title":"Residual attention network for image classification,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2505.05943","last_updated":"2025-05-09T10:36:30Z","snapshot_observed_at":"2026-08-16T14:49:47.657763Z","submitted_at":"2025-05-09T10:36:30Z","title":"Achieving 3D Attention via Triplet Squeeze and Excitation Block","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-15T22:55:38.592817Z"},"links":{"cited_paper":"/paper/1704.06904","citing_paper":"/paper/2505.05943"},"observation_digest":"sha256:252d858153fadb4254160e30d331bee04939f1a47d8cabda6910fc1ca7baac78","observation_id":"ae9971a0-9b4b-4487-a19e-0ff897598320","resolution":{"observed_at":"2026-08-15T22:55:38.592817Z","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":"2026-08-15T22:55:39.180297Z","title":"Best fit activation functions for attention mechanism: Comparison and enhancement,","venue":null,"work_id":"84f65648-50fb-44f8-847a-57217bb14251","year":2023},"citing_paper":{"arxiv_id":"2505.05943","last_updated":"2025-05-09T10:36:30Z","snapshot_observed_at":"2026-08-16T14:49:47.657763Z","submitted_at":"2025-05-09T10:36:30Z","title":"Achieving 3D Attention via Triplet Squeeze and Excitation Block","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-15T22:55:38.596955Z"},"links":{"citing_paper":"/paper/2505.05943"},"observation_digest":"sha256:32476e0455d7a40383ec44c68e2aff3ea223f73810d2bcb44bfb4777276d5f07","observation_id":"be94c61a-9037-4705-aba8-3acdb94ea401","resolution":{"observed_at":"2026-08-15T22:55:39.185730Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T22:55:39.163899Z","title":"Facial expression recognition using residual masking network,","venue":null,"work_id":"09c4d697-82e8-4c7a-85e9-ff99df732f2e","year":2020},"citing_paper":{"arxiv_id":"2505.05943","last_updated":"2025-05-09T10:36:30Z","snapshot_observed_at":"2026-08-16T14:49:47.657763Z","submitted_at":"2025-05-09T10:36:30Z","title":"Achieving 3D Attention via Triplet Squeeze and Excitation Block","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-15T22:55:38.600709Z"},"links":{"citing_paper":"/paper/2505.05943"},"observation_digest":"sha256:cc03948f7149d9252a110c3219cee82efffb29f27f9c9b7c6579b7600c97823f","observation_id":"d6c53047-1b81-4ece-b2bd-8ff89a85d996","resolution":{"observed_at":"2026-08-15T22:55:39.169268Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T22:55:39.149192Z","title":"A novel facial emotion recognition model using segmentation vgg- 19 architecture - international journal of information technology,","venue":null,"work_id":"5bc99b48-fb5c-400d-8a73-ba734efcd0ce","year":2023},"citing_paper":{"arxiv_id":"2505.05943","last_updated":"2025-05-09T10:36:30Z","snapshot_observed_at":"2026-08-16T14:49:47.657763Z","submitted_at":"2025-05-09T10:36:30Z","title":"Achieving 3D Attention via Triplet Squeeze and Excitation Block","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-15T22:55:38.604458Z"},"links":{"citing_paper":"/paper/2505.05943"},"observation_digest":"sha256:e580cae822c0cdea6cad00c24d615008752d0c4e6a71b0b4b5d3ed7ddde5f43f","observation_id":"ebab86a0-34b6-421b-8d00-bf8868c28333","resolution":{"observed_at":"2026-08-15T22:55:39.153599Z","resolver_source":"raw_fallback","status":"malformed_identifier"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T22:55:39.134532Z","title":null,"venue":null,"work_id":"67efd0ef-4f04-4bcd-b36c-ee8bd8d3656a","year":2015},"citing_paper":{"arxiv_id":"2505.05943","last_updated":"2025-05-09T10:36:30Z","snapshot_observed_at":"2026-08-16T14:49:47.657763Z","submitted_at":"2025-05-09T10:36:30Z","title":"Achieving 3D Attention via Triplet Squeeze and Excitation Block","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-15T22:55:38.608057Z"},"links":{"citing_paper":"/paper/2505.05943"},"observation_digest":"sha256:164026230ceee8ce93d8c39c61492435cdb3a26d2fa3b52d08a8e81dade46d22","observation_id":"e43b1545-947c-431e-9a0c-dc510e54cc3a","resolution":{"observed_at":"2026-08-15T22:55:39.139067Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T22:55:39.118888Z","title":"Deep-emotion: Facial expression recognition using attentional convolutional network,","venue":null,"work_id":"fa64ac48-a1e6-4f40-98a3-b8e5d119005e","year":2021},"citing_paper":{"arxiv_id":"2505.05943","last_updated":"2025-05-09T10:36:30Z","snapshot_observed_at":"2026-08-16T14:49:47.657763Z","submitted_at":"2025-05-09T10:36:30Z","title":"Achieving 3D Attention via Triplet Squeeze and Excitation Block","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-15T22:55:38.611621Z"},"links":{"citing_paper":"/paper/2505.05943"},"observation_digest":"sha256:4c9e2daea25f1272641159c831bcc5ce09ecfd3985d11fd65a555328d6f78643","observation_id":"2f766ce4-c892-41d6-b6e9-d491d3aeb422","resolution":{"observed_at":"2026-08-15T22:55:39.124630Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T22:55:39.099666Z","title":"Facial emotion recognition: State of the art performance on fer2013,","venue":null,"work_id":"ce233547-e87b-4c72-ae0d-40631773e17d","year":2021},"citing_paper":{"arxiv_id":"2505.05943","last_updated":"2025-05-09T10:36:30Z","snapshot_observed_at":"2026-08-16T14:49:47.657763Z","submitted_at":"2025-05-09T10:36:30Z","title":"Achieving 3D Attention via Triplet Squeeze and Excitation Block","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-15T22:55:38.615744Z"},"links":{"citing_paper":"/paper/2505.05943"},"observation_digest":"sha256:c0af5797235b163296bb0a7cae05b7c2f5ba8c8f6e19aa9e60e736c9af08fcbf","observation_id":"4b91d3ac-7cb3-4664-b75e-0452d2e360c3","resolution":{"observed_at":"2026-08-15T22:55:39.105519Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T22:55:38.620252Z","title":"Ad-corre: Adaptive correlation-based loss for facial expression recognition in the wild,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.05943","last_updated":"2025-05-09T10:36:30Z","snapshot_observed_at":"2026-08-16T14:49:47.657763Z","submitted_at":"2025-05-09T10:36:30Z","title":"Achieving 3D Attention via Triplet Squeeze and Excitation Block","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-15T22:55:38.620252Z"},"links":{"citing_paper":"/paper/2505.05943"},"observation_digest":"sha256:d175eedfc6265125f741cf63f5b3777ade626297dee25865c5a4623b05b33b5f","observation_id":"754b7f8c-5fb6-4fe9-979b-cd23312b8419","resolution":{"observed_at":"2026-08-15T22:55:38.620252Z","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":"2026-08-15T22:55:39.073957Z","title":"Facial expression recogni- tion with deep learning,","venue":null,"work_id":"c16c6515-affe-479d-a0e5-b35695a6c0be","year":2020},"citing_paper":{"arxiv_id":"2505.05943","last_updated":"2025-05-09T10:36:30Z","snapshot_observed_at":"2026-08-16T14:49:47.657763Z","submitted_at":"2025-05-09T10:36:30Z","title":"Achieving 3D Attention via Triplet Squeeze and Excitation Block","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-15T22:55:38.623980Z"},"links":{"citing_paper":"/paper/2505.05943"},"observation_digest":"sha256:87c6510797a9ad390098f78344cf9ad1930102b3888fcc8e91612d763e86b27d","observation_id":"0fde30e2-17a3-439e-bacd-10d1ca335efd","resolution":{"observed_at":"2026-08-15T22:55:39.078648Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1007/s41870-023-01184-z","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:55:38.666659Z","title":"A novel facial emotion recognition model using segmentation vgg- 19 architecture,","venue":null,"work_id":"b8426135-90ca-4c81-baa6-7ec88e9c7c20","year":2023},"citing_paper":{"arxiv_id":"2505.05943","last_updated":"2025-05-09T10:36:30Z","snapshot_observed_at":"2026-08-16T14:49:47.657763Z","submitted_at":"2025-05-09T10:36:30Z","title":"Achieving 3D Attention via Triplet Squeeze and Excitation Block","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-15T22:55:38.627650Z"},"links":{"citing_paper":"/paper/2505.05943"},"observation_digest":"sha256:a48a9243b2c8b3854e92d50a3b3622cbd3e12f6ef4baeb88e1757a0f717f2305","observation_id":"52615bdc-f2d2-413f-9340-144f231af72c","resolution":{"observed_at":"2026-08-15T22:55:38.672902Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T22:55:39.058543Z","title":"Local multi-head channel self- attention for facial expression recognition,","venue":null,"work_id":"7b9798fc-4296-47e7-a6c1-f25225a9e12a","year":null},"citing_paper":{"arxiv_id":"2505.05943","last_updated":"2025-05-09T10:36:30Z","snapshot_observed_at":"2026-08-16T14:49:47.657763Z","submitted_at":"2025-05-09T10:36:30Z","title":"Achieving 3D Attention via Triplet Squeeze and Excitation Block","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-15T22:55:38.631572Z"},"links":{"citing_paper":"/paper/2505.05943"},"observation_digest":"sha256:9efe6e1bdede9e93dcc2f08cea28d597af7612f7d81490c209c3aced4a063b15","observation_id":"128982ca-2405-4f51-a1fc-a055104b58f4","resolution":{"observed_at":"2026-08-15T22:55:39.065006Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1910.03151","last_updated":"2020-04-07T13:53:51Z","snapshot_observed_at":"2026-07-06T08:27:36.865513Z","submitted_at":"2019-10-08T01:14:26Z","title":"ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1910.03151","snapshot_observed_at":"2026-08-15T22:55:38.572727Z","title":"Available: https://arxiv.org/abs/1910.03151","venue":null,"work_id":null,"year":1910},"citing_paper":{"arxiv_id":"2505.05943","last_updated":"2025-05-09T10:36:30Z","snapshot_observed_at":"2026-08-16T14:49:47.657763Z","submitted_at":"2025-05-09T10:36:30Z","title":"Achieving 3D Attention via Triplet Squeeze and Excitation Block","version":1},"reference_index":2019,"source":"pdf_text","source_observed_at":"2026-08-15T22:55:38.572727Z"},"links":{"cited_paper":"/paper/1910.03151","citing_paper":"/paper/2505.05943"},"observation_digest":"sha256:69d782a22fbaa81ce8c45b89c9ad8ab878c71307b6262d8ae72a43e4875a089c","observation_id":"cc1d8b4b-7481-4c7f-a5c1-b0eb637bb87d","resolution":{"observed_at":"2026-08-15T22:55:38.572727Z","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":"2026-08-15T22:55:39.040259Z","title":"Available: https://www.mdpi.com/2078-2489/13/9/419","venue":null,"work_id":"cd392e77-d08a-4fca-b6b1-fc10fc688347","year":null},"citing_paper":{"arxiv_id":"2505.05943","last_updated":"2025-05-09T10:36:30Z","snapshot_observed_at":"2026-08-16T14:49:47.657763Z","submitted_at":"2025-05-09T10:36:30Z","title":"Achieving 3D Attention via Triplet Squeeze and Excitation Block","version":1},"reference_index":2022,"source":"pdf_text","source_observed_at":"2026-08-15T22:55:38.635413Z"},"links":{"citing_paper":"/paper/2505.05943"},"observation_digest":"sha256:549eb6da9c1417a3df1e13932a8ffaefebb72da95c9007f1a6c6941cae391b79","observation_id":"339055d1-5f29-4545-a1af-091946a2fe6a","resolution":{"observed_at":"2026-08-15T22:55:39.045450Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2505.05943","last_updated":"2025-05-09T10:36:30Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-16T14:49:47.657763Z","submitted_at":"2025-05-09T10:36:30Z","title":"Achieving 3D Attention via Triplet Squeeze and Excitation Block"},"reference_resolution":{"displayed":41,"state_counts":{"malformed_identifier":2,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":21,"verified_exact":5,"verified_fuzzy":13},"total_outbound_references":41},"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":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"thesis":"As of 16 August 2026, this Paper Citation Record lists 41 of 41 outbound references and 0 inbound Pith citation observations for arXiv:2505.05943."}