{"as_of":"2026-08-10T19:34:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:8afcc2e881e55d88c0c260ee75094f4c8f0fba938d44547b49ad7890d615b95a","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":"2026-07-13T16:08:30.031334Z","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":"2026-08-10T06:31:04.303077+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/2603.28759/citation-record","integrity":"/paper/2603.28759/integrity","json":"/paper/2603.28759/citation-record.json","paper":"/paper/2603.28759"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-13T16:08:30.031334Z","title":"Learning optical flow from still images","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2603.28759","last_updated":"2026-05-31T17:37:40Z","snapshot_observed_at":"2026-08-10T13:07:04.823949Z","submitted_at":"2026-03-30T17:58:12Z","title":"FlowIt: Global Matching via Hierarchical Transformers and Optimal Transport for Optical Flow","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-07-13T16:08:30.031334Z"},"links":{"citing_paper":"/paper/2603.28759"},"observation_digest":"sha256:cd32e52f804cb79d805c18809cc6da566436540cf36268b735a5719305285f39","observation_id":"a2ad69eb-6058-40c9-bbc5-f4f35da8b5fb","resolution":{"observed_at":"2026-07-13T16:08:30.031334Z","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":"2026-07-13T16:08:30.031334Z","title":"A computational framework and an algorithm for the measurement of visual motion.IJCV, 2:283–310, 1989","venue":null,"work_id":null,"year":1989},"citing_paper":{"arxiv_id":"2603.28759","last_updated":"2026-05-31T17:37:40Z","snapshot_observed_at":"2026-08-10T13:07:04.823949Z","submitted_at":"2026-03-30T17:58:12Z","title":"FlowIt: Global Matching via Hierarchical Transformers and Optimal Transport for Optical Flow","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-07-13T16:08:30.031334Z"},"links":{"citing_paper":"/paper/2603.28759"},"observation_digest":"sha256:c40092bd3fcc13166354b248326c6dfcae2044b6867b87b2365e673d892437ca","observation_id":"f86003f7-9bfd-443d-b3d7-a0ef97083264","resolution":{"observed_at":"2026-07-13T16:08:30.031334Z","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":"2026-07-13T16:08:30.031334Z","title":"MEM- FOF: High-resolution training for memory-efficient multi-frame optical flow estima- tion","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2603.28759","last_updated":"2026-05-31T17:37:40Z","snapshot_observed_at":"2026-08-10T13:07:04.823949Z","submitted_at":"2026-03-30T17:58:12Z","title":"FlowIt: Global Matching via Hierarchical Transformers and Optimal Transport for Optical Flow","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-07-13T16:08:30.031334Z"},"links":{"citing_paper":"/paper/2603.28759"},"observation_digest":"sha256:536964939f5ce6fe54c2e77d1093f86c6a974ea3f66c2a32c9d75a29c485ff10","observation_id":"748d52ba-52ad-41cc-bd76-7cc3e2a9a994","resolution":{"observed_at":"2026-07-13T16:08:30.031334Z","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":"2026-07-13T16:08:30.031334Z","title":"PMBP: Patch- match belief propagation for correspondence problems","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2603.28759","last_updated":"2026-05-31T17:37:40Z","snapshot_observed_at":"2026-08-10T13:07:04.823949Z","submitted_at":"2026-03-30T17:58:12Z","title":"FlowIt: Global Matching via Hierarchical Transformers and Optimal Transport for Optical Flow","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-07-13T16:08:30.031334Z"},"links":{"citing_paper":"/paper/2603.28759"},"observation_digest":"sha256:524411c7ab55bd70b4e6b896a617433dbd07be7020ba215f3e17967ba90596ec","observation_id":"fb69b4f1-64e8-4a72-9951-06cc03871c35","resolution":{"observed_at":"2026-07-13T16:08:30.031334Z","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":"2026-07-13T16:08:30.031334Z","title":"A framework for the robust estimation of optical flow","venue":null,"work_id":null,"year":1993},"citing_paper":{"arxiv_id":"2603.28759","last_updated":"2026-05-31T17:37:40Z","snapshot_observed_at":"2026-08-10T13:07:04.823949Z","submitted_at":"2026-03-30T17:58:12Z","title":"FlowIt: Global Matching via Hierarchical Transformers and Optimal Transport for Optical Flow","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-07-13T16:08:30.031334Z"},"links":{"citing_paper":"/paper/2603.28759"},"observation_digest":"sha256:d13b275d5688f266752a80ffb046d71973dae97acfa6d09aa3d586b94e8da7ad","observation_id":"1485c4b5-4d7b-4225-be2d-befd9a9d55d7","resolution":{"observed_at":"2026-07-13T16:08:30.031334Z","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":"2026-07-13T16:08:30.031334Z","title":"High accuracy optical flow estimation based on a theory for warping","venue":null,"work_id":null,"year":2004},"citing_paper":{"arxiv_id":"2603.28759","last_updated":"2026-05-31T17:37:40Z","snapshot_observed_at":"2026-08-10T13:07:04.823949Z","submitted_at":"2026-03-30T17:58:12Z","title":"FlowIt: Global Matching via Hierarchical Transformers and Optimal Transport for Optical Flow","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-07-13T16:08:30.031334Z"},"links":{"citing_paper":"/paper/2603.28759"},"observation_digest":"sha256:5ef2de3efbdfcbc9f8cb02b6e582281f0c7bfc6601d77c858f4af7defc15345c","observation_id":"be61ef6f-e2fd-4c78-bc61-8e5d992eabf1","resolution":{"observed_at":"2026-07-13T16:08:30.031334Z","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":"2026-07-13T16:08:30.031334Z","title":"A naturalistic open source movie for optical flow evaluation","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2603.28759","last_updated":"2026-05-31T17:37:40Z","snapshot_observed_at":"2026-08-10T13:07:04.823949Z","submitted_at":"2026-03-30T17:58:12Z","title":"FlowIt: Global Matching via Hierarchical Transformers and Optimal Transport for Optical Flow","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-07-13T16:08:30.031334Z"},"links":{"citing_paper":"/paper/2603.28759"},"observation_digest":"sha256:a82263cfaab07a1f4f832eebef934541ff35f80db1f7bdd10e732cbf552337b7","observation_id":"614f9eb5-660b-4dd4-9598-6bbf7b848235","resolution":{"observed_at":"2026-07-13T16:08:30.031334Z","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":"2026-07-13T16:08:30.031334Z","title":"Sinkhorn distances: Lightspeed computation of optimal transport","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2603.28759","last_updated":"2026-05-31T17:37:40Z","snapshot_observed_at":"2026-08-10T13:07:04.823949Z","submitted_at":"2026-03-30T17:58:12Z","title":"FlowIt: Global Matching via Hierarchical Transformers and Optimal Transport for Optical Flow","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-07-13T16:08:30.031334Z"},"links":{"citing_paper":"/paper/2603.28759"},"observation_digest":"sha256:df93f5fb6caa0e484d3e0aab2a9d03c95586badc6102fd6de3cc931537147b50","observation_id":"258cdc90-8fb7-4d12-a38e-af5c57de1653","resolution":{"observed_at":"2026-07-13T16:08:30.031334Z","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":"2026-07-13T16:08:30.031334Z","title":"Explicit motion disentangling for efficient optical flow estimation","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2603.28759","last_updated":"2026-05-31T17:37:40Z","snapshot_observed_at":"2026-08-10T13:07:04.823949Z","submitted_at":"2026-03-30T17:58:12Z","title":"FlowIt: Global Matching via Hierarchical Transformers and Optimal Transport for Optical Flow","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-07-13T16:08:30.031334Z"},"links":{"citing_paper":"/paper/2603.28759"},"observation_digest":"sha256:c8b1014b6b67f0cf0e5efd124c8ed6738457dde32c9b72e21d19dac6be33928d","observation_id":"7b49862c-9dd9-4ffc-bf9c-b0374e39d51e","resolution":{"observed_at":"2026-07-13T16:08:30.031334Z","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":"2026-07-13T16:08:30.031334Z","title":"Memflow: Optical flow estimation and prediction with memory","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2603.28759","last_updated":"2026-05-31T17:37:40Z","snapshot_observed_at":"2026-08-10T13:07:04.823949Z","submitted_at":"2026-03-30T17:58:12Z","title":"FlowIt: Global Matching via Hierarchical Transformers and Optimal Transport for Optical Flow","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-07-13T16:08:30.031334Z"},"links":{"citing_paper":"/paper/2603.28759"},"observation_digest":"sha256:8f77896c14c71d3e16be505583199dbcfd5f7b4079eed056fc4af8a2382dcdf5","observation_id":"07ca7231-2448-4321-ac08-be017a66f5e6","resolution":{"observed_at":"2026-07-13T16:08:30.031334Z","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":"2026-07-13T16:08:30.031334Z","title":"Rethinking optical flow from geometric matching consistent perspective","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2603.28759","last_updated":"2026-05-31T17:37:40Z","snapshot_observed_at":"2026-08-10T13:07:04.823949Z","submitted_at":"2026-03-30T17:58:12Z","title":"FlowIt: Global Matching via Hierarchical Transformers and Optimal Transport for Optical Flow","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-07-13T16:08:30.031334Z"},"links":{"citing_paper":"/paper/2603.28759"},"observation_digest":"sha256:ce3f45ecae343a16b084677b27f32a9b3ac0c1629f6e55a5a118fc1ffdb569aa","observation_id":"f9aa2b8c-67dd-4ef6-9d10-536f75d44888","resolution":{"observed_at":"2026-07-13T16:08:30.031334Z","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":"2026-07-13T16:08:30.031334Z","title":"FlowNet: Learning optical flow with convolutional networks","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2603.28759","last_updated":"2026-05-31T17:37:40Z","snapshot_observed_at":"2026-08-10T13:07:04.823949Z","submitted_at":"2026-03-30T17:58:12Z","title":"FlowIt: Global Matching via Hierarchical Transformers and Optimal Transport for Optical Flow","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-07-13T16:08:30.031334Z"},"links":{"citing_paper":"/paper/2603.28759"},"observation_digest":"sha256:603153c9cc39e903150b6b0386a1f13b54c671348099b300f3fe1a8e1825c8bc","observation_id":"972e14d7-4225-431f-989c-ae9139747968","resolution":{"observed_at":"2026-07-13T16:08:30.031334Z","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":"2026-07-13T16:08:30.031334Z","title":"Flow-edge guided video completion","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2603.28759","last_updated":"2026-05-31T17:37:40Z","snapshot_observed_at":"2026-08-10T13:07:04.823949Z","submitted_at":"2026-03-30T17:58:12Z","title":"FlowIt: Global Matching via Hierarchical Transformers and Optimal Transport for Optical Flow","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-07-13T16:08:30.031334Z"},"links":{"citing_paper":"/paper/2603.28759"},"observation_digest":"sha256:23c13596833c8495faef57783d072f15df63c5d10d5345478f9be588cfb222ce","observation_id":"15b01402-706c-467f-8cc8-6204d373a4b6","resolution":{"observed_at":"2026-07-13T16:08:30.031334Z","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":"2026-07-13T16:08:30.031334Z","title":"Vision meets robotics: The KITTI dataset.IJCV, 32(11):1231–1237, 2013","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2603.28759","last_updated":"2026-05-31T17:37:40Z","snapshot_observed_at":"2026-08-10T13:07:04.823949Z","submitted_at":"2026-03-30T17:58:12Z","title":"FlowIt: Global Matching via Hierarchical Transformers and Optimal Transport for Optical Flow","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-07-13T16:08:30.031334Z"},"links":{"citing_paper":"/paper/2603.28759"},"observation_digest":"sha256:03ddf54fb03cda42e2275902c82e690e585e1b5c24ef0e8c0a08d9b56b69a670","observation_id":"886c6526-0113-4db8-834e-a7b49049abe2","resolution":{"observed_at":"2026-07-13T16:08:30.031334Z","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":"2026-07-13T16:08:30.031334Z","title":"RealFlow: EM-based realistic optical flow dataset generation from videos","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2603.28759","last_updated":"2026-05-31T17:37:40Z","snapshot_observed_at":"2026-08-10T13:07:04.823949Z","submitted_at":"2026-03-30T17:58:12Z","title":"FlowIt: Global Matching via Hierarchical Transformers and Optimal Transport for Optical Flow","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-07-13T16:08:30.031334Z"},"links":{"citing_paper":"/paper/2603.28759"},"observation_digest":"sha256:8eace2ca6f6b041e43162c610e0aef0e645088025df46ad257cd65496a77959b","observation_id":"c80e85f4-e943-4ba4-bf77-b0745ab0e710","resolution":{"observed_at":"2026-07-13T16:08:30.031334Z","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":"2026-07-13T16:08:30.031334Z","title":"Determining optical flow.Artificial intelli- gence, 17(1-3):185–203, 1981","venue":null,"work_id":null,"year":1981},"citing_paper":{"arxiv_id":"2603.28759","last_updated":"2026-05-31T17:37:40Z","snapshot_observed_at":"2026-08-10T13:07:04.823949Z","submitted_at":"2026-03-30T17:58:12Z","title":"FlowIt: Global Matching via Hierarchical Transformers and Optimal Transport for Optical Flow","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-07-13T16:08:30.031334Z"},"links":{"citing_paper":"/paper/2603.28759"},"observation_digest":"sha256:4909d829f5eb8c6c8ff5e393fea145d4356522a33b13d40938faf336675eb72d","observation_id":"f4ad1be3-ab1f-4cef-8de9-c25d2ec77245","resolution":{"observed_at":"2026-07-13T16:08:30.031334Z","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":"2026-07-13T16:08:30.031334Z","title":"FlowFormer: A transformer architecture for optical flow","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2603.28759","last_updated":"2026-05-31T17:37:40Z","snapshot_observed_at":"2026-08-10T13:07:04.823949Z","submitted_at":"2026-03-30T17:58:12Z","title":"FlowIt: Global Matching via Hierarchical Transformers and Optimal Transport for Optical Flow","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-07-13T16:08:30.031334Z"},"links":{"citing_paper":"/paper/2603.28759"},"observation_digest":"sha256:3494f7dbd0e02d4151903b141ee67eae0abe54579235ea1de0766adc6edb8ffb","observation_id":"5dd0fd85-4c2a-4ec2-87cf-31c7833de2ca","resolution":{"observed_at":"2026-07-13T16:08:30.031334Z","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":"2026-07-13T16:08:30.031334Z","title":"Real-time intermediate flow estimation for video frame interpolation","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2603.28759","last_updated":"2026-05-31T17:37:40Z","snapshot_observed_at":"2026-08-10T13:07:04.823949Z","submitted_at":"2026-03-30T17:58:12Z","title":"FlowIt: Global Matching via Hierarchical Transformers and Optimal Transport for Optical Flow","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-07-13T16:08:30.031334Z"},"links":{"citing_paper":"/paper/2603.28759"},"observation_digest":"sha256:5c3aa574da0e7652f64702b7c28a7bfdca883466052618851beea8c19166d4b9","observation_id":"4ff981ab-39d6-4f78-92d6-c48e639e1929","resolution":{"observed_at":"2026-07-13T16:08:30.031334Z","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":"2026-07-13T16:08:30.031334Z","title":"LiteFlowNet3: Resolving Correspondence Ambi- guity for More Accurate Optical Flow Estimation","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2603.28759","last_updated":"2026-05-31T17:37:40Z","snapshot_observed_at":"2026-08-10T13:07:04.823949Z","submitted_at":"2026-03-30T17:58:12Z","title":"FlowIt: Global Matching via Hierarchical Transformers and Optimal Transport for Optical Flow","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-07-13T16:08:30.031334Z"},"links":{"citing_paper":"/paper/2603.28759"},"observation_digest":"sha256:61dd05c64d8e5e12976d458d1fda6041f21fe24990dc2bdf95e7792c73798c71","observation_id":"4bdaa668-3402-4cd4-9c24-2d318e891f95","resolution":{"observed_at":"2026-07-13T16:08:30.031334Z","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":"2026-07-13T16:08:30.031334Z","title":"LiteFlowNet: A Lightweight Con- volutional Neural Network for Optical Flow Estimation","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2603.28759","last_updated":"2026-05-31T17:37:40Z","snapshot_observed_at":"2026-08-10T13:07:04.823949Z","submitted_at":"2026-03-30T17:58:12Z","title":"FlowIt: Global Matching via Hierarchical Transformers and Optimal Transport for Optical Flow","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-07-13T16:08:30.031334Z"},"links":{"citing_paper":"/paper/2603.28759"},"observation_digest":"sha256:d7dcbe1561047576171772baceed965b877acca4899feb3f00368c0bebc9fad8","observation_id":"6430b978-4296-425e-9720-e1dbff9711a5","resolution":{"observed_at":"2026-07-13T16:08:30.031334Z","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":"2026-07-13T16:08:30.031334Z","title":"A Lightweight Optical Flow CNN —Revisiting Data Fidelity and Regularization .IEEE TPAMI, 43(08):2555–2569,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2603.28759","last_updated":"2026-05-31T17:37:40Z","snapshot_observed_at":"2026-08-10T13:07:04.823949Z","submitted_at":"2026-03-30T17:58:12Z","title":"FlowIt: Global Matching via Hierarchical Transformers and Optimal Transport for Optical Flow","version":2},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-07-13T16:08:30.031334Z"},"links":{"citing_paper":"/paper/2603.28759"},"observation_digest":"sha256:3a3ca002fd03908571450a31ef5e114d901a2096d658c1ed8bfbcfaa7bfda723","observation_id":"aa51cd00-de4d-4146-b8d7-d2baa8973a62","resolution":{"observed_at":"2026-07-13T16:08:30.031334Z","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":"2026-07-13T16:08:30.031334Z","title":"FlowNet 2.0: Evolution of optical flow estimation with deep networks","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2603.28759","last_updated":"2026-05-31T17:37:40Z","snapshot_observed_at":"2026-08-10T13:07:04.823949Z","submitted_at":"2026-03-30T17:58:12Z","title":"FlowIt: Global Matching via Hierarchical Transformers and Optimal Transport for Optical Flow","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-07-13T16:08:30.031334Z"},"links":{"citing_paper":"/paper/2603.28759"},"observation_digest":"sha256:6a20b392a2d0b4ae86ab9d434f8b7c5148f25ebb21cccff1a0fcd77b9bcd477d","observation_id":"8ee5af4d-1e47-482d-8ef2-98a3a187d1a0","resolution":{"observed_at":"2026-07-13T16:08:30.031334Z","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":"2026-07-13T16:08:30.031334Z","title":"CCMR: High reso- lution optical flow estimation via coarse-to-fine context-guided motion reasoning","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2603.28759","last_updated":"2026-05-31T17:37:40Z","snapshot_observed_at":"2026-08-10T13:07:04.823949Z","submitted_at":"2026-03-30T17:58:12Z","title":"FlowIt: Global Matching via Hierarchical Transformers and Optimal Transport for Optical Flow","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-07-13T16:08:30.031334Z"},"links":{"citing_paper":"/paper/2603.28759"},"observation_digest":"sha256:816c399c7b439370acbc82fbce214f59314ee40cdc4e0020d4e9e1b2c7a08041","observation_id":"f4e9913e-b565-4c18-980d-d287e0f511ca","resolution":{"observed_at":"2026-07-13T16:08:30.031334Z","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":"2026-07-13T16:08:30.031334Z","title":"MS- RAFT+: high resolution multi-scale raft.IJCV, 132(5):1835–1856, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2603.28759","last_updated":"2026-05-31T17:37:40Z","snapshot_observed_at":"2026-08-10T13:07:04.823949Z","submitted_at":"2026-03-30T17:58:12Z","title":"FlowIt: Global Matching via Hierarchical Transformers and Optimal Transport for Optical Flow","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-07-13T16:08:30.031334Z"},"links":{"citing_paper":"/paper/2603.28759"},"observation_digest":"sha256:f0058d3464ce0e73db98ce8053f6c5cc79664c75476220a877dd9dcd4e7e6983","observation_id":"abd79a51-8a3d-46ed-9804-0356409caeb0","resolution":{"observed_at":"2026-07-13T16:08:30.031334Z","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":"2026-07-13T16:08:30.031334Z","title":"Computer vision for autonomous vehicles: Problems, datasets and state of the art.Foundations and trends® in computer graphics and vision, 12(1–3):1–308, 2020","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2603.28759","last_updated":"2026-05-31T17:37:40Z","snapshot_observed_at":"2026-08-10T13:07:04.823949Z","submitted_at":"2026-03-30T17:58:12Z","title":"FlowIt: Global Matching via Hierarchical Transformers and Optimal Transport for Optical Flow","version":2},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-07-13T16:08:30.031334Z"},"links":{"citing_paper":"/paper/2603.28759"},"observation_digest":"sha256:b07988fe2333297bb78217b5d4b41dbcaca63d1cf9a782a0f352ddba7d798213","observation_id":"511ec5cd-ec8b-4697-86ee-0fa7a9cc3417","resolution":{"observed_at":"2026-07-13T16:08:30.031334Z","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":"2026-07-13T16:08:30.031334Z","title":"DistractFlow: Improving optical flow estimation via realistic distractions and pseudo-labeling","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2603.28759","last_updated":"2026-05-31T17:37:40Z","snapshot_observed_at":"2026-08-10T13:07:04.823949Z","submitted_at":"2026-03-30T17:58:12Z","title":"FlowIt: Global Matching via Hierarchical Transformers and Optimal Transport for Optical Flow","version":2},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-07-13T16:08:30.031334Z"},"links":{"citing_paper":"/paper/2603.28759"},"observation_digest":"sha256:ced01b4a8466b91c5fec66b4517c30d59999b8ca555436344fad14f6b4525575","observation_id":"07713d32-bca9-452c-a52d-7360de05a380","resolution":{"observed_at":"2026-07-13T16:08:30.031334Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2104.02409","last_updated":"2021-07-29T20:59:31Z","snapshot_observed_at":"2026-08-10T16:45:27.125261Z","submitted_at":"2021-04-06T10:32:03Z","title":"Learning to Estimate Hidden Motions with Global Motion Aggregation","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2104.02409","snapshot_observed_at":"2026-07-13T16:08:30.031334Z","title":"Learn- ing to estimate hidden motions with global motion aggregation.arXiv preprint arXiv:2104.02409, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2603.28759","last_updated":"2026-05-31T17:37:40Z","snapshot_observed_at":"2026-08-10T13:07:04.823949Z","submitted_at":"2026-03-30T17:58:12Z","title":"FlowIt: Global Matching via Hierarchical Transformers and Optimal Transport for Optical Flow","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-07-13T16:08:30.031334Z"},"links":{"cited_paper":"/paper/2104.02409","citing_paper":"/paper/2603.28759"},"observation_digest":"sha256:077a6019c9192c24b164e56d8dfed8fed0ac0a08aa1c945cf63544a1fe24f49c","observation_id":"5b56373a-814f-4205-8da2-7297151bd4f5","resolution":{"observed_at":"2026-07-13T16:08:30.031334Z","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":"2026-07-13T16:08:30.031334Z","title":"Learning optical flow from a few matches","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2603.28759","last_updated":"2026-05-31T17:37:40Z","snapshot_observed_at":"2026-08-10T13:07:04.823949Z","submitted_at":"2026-03-30T17:58:12Z","title":"FlowIt: Global Matching via Hierarchical Transformers and Optimal Transport for Optical Flow","version":2},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-07-13T16:08:30.031334Z"},"links":{"citing_paper":"/paper/2603.28759"},"observation_digest":"sha256:ad0e0111b7e469c9c4871c845194d70b73f37c37eb3e9841638ea3a832baf9ec","observation_id":"62852fa1-aee6-4b31-a7dc-be17600924b2","resolution":{"observed_at":"2026-07-13T16:08:30.031334Z","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":"2026-07-13T16:08:30.031334Z","title":"EffiScene: Efficient per-pixel rigidity inference for unsupervised joint learning of optical flow, depth, camera pose and motion segmentation","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2603.28759","last_updated":"2026-05-31T17:37:40Z","snapshot_observed_at":"2026-08-10T13:07:04.823949Z","submitted_at":"2026-03-30T17:58:12Z","title":"FlowIt: Global Matching via Hierarchical Transformers and Optimal Transport for Optical Flow","version":2},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-07-13T16:08:30.031334Z"},"links":{"citing_paper":"/paper/2603.28759"},"observation_digest":"sha256:4c02605bce2eaf703fb9606720c131845b55e36fe9a9b2b9608ec831948df162","observation_id":"dbe1f8f4-4ea5-465e-9fe4-758d57db72d7","resolution":{"observed_at":"2026-07-13T16:08:30.031334Z","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":"2026-07-13T16:08:30.031334Z","title":"What matters in unsupervised optical flow","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2603.28759","last_updated":"2026-05-31T17:37:40Z","snapshot_observed_at":"2026-08-10T13:07:04.823949Z","submitted_at":"2026-03-30T17:58:12Z","title":"FlowIt: Global Matching via Hierarchical Transformers and Optimal Transport for Optical Flow","version":2},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-07-13T16:08:30.031334Z"},"links":{"citing_paper":"/paper/2603.28759"},"observation_digest":"sha256:b26988001fdd8512148c27449fcb21b8af83e3620490540fbf673c312a4a6a88","observation_id":"f54506fc-3fa3-42bc-b765-cc5a835ee9aa","resolution":{"observed_at":"2026-07-13T16:08:30.031334Z","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":"2026-07-13T16:08:30.031334Z","title":"AnyFlow: Arbitrary scale optical flow with implicit neural representation","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2603.28759","last_updated":"2026-05-31T17:37:40Z","snapshot_observed_at":"2026-08-10T13:07:04.823949Z","submitted_at":"2026-03-30T17:58:12Z","title":"FlowIt: Global Matching via Hierarchical Transformers and Optimal Transport for Optical Flow","version":2},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-07-13T16:08:30.031334Z"},"links":{"citing_paper":"/paper/2603.28759"},"observation_digest":"sha256:3098476e08526315ea5a4c102290bbf5105606f73c6883e5f8776fe1cdd93a5b","observation_id":"4e5da885-31fe-4546-bc90-9ff55651aa0e","resolution":{"observed_at":"2026-07-13T16:08:30.031334Z","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":"2026-07-13T16:08:30.031334Z","title":"Deep video inpaint- ing","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2603.28759","last_updated":"2026-05-31T17:37:40Z","snapshot_observed_at":"2026-08-10T13:07:04.823949Z","submitted_at":"2026-03-30T17:58:12Z","title":"FlowIt: Global Matching via Hierarchical Transformers and Optimal Transport for Optical Flow","version":2},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-07-13T16:08:30.031334Z"},"links":{"citing_paper":"/paper/2603.28759"},"observation_digest":"sha256:b4e09336d3a85f0fb222aca83616bae87844f1556a039774c88b6d30a1bcc4aa","observation_id":"5ef2554f-0e1a-45ed-a9a3-c7df731d6b3a","resolution":{"observed_at":"2026-07-13T16:08:30.031334Z","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":"2026-07-13T16:08:30.031334Z","title":"The HCI benchmark suite: Stereo and flow ground truth with uncertainties for urban autonomous driving","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2603.28759","last_updated":"2026-05-31T17:37:40Z","snapshot_observed_at":"2026-08-10T13:07:04.823949Z","submitted_at":"2026-03-30T17:58:12Z","title":"FlowIt: Global Matching via Hierarchical Transformers and Optimal Transport for Optical Flow","version":2},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-07-13T16:08:30.031334Z"},"links":{"citing_paper":"/paper/2603.28759"},"observation_digest":"sha256:3f65f40af5d04fb436d315842c0dc3a3adef491e1609cf74ef16312ef4f4c2c2","observation_id":"859c6d61-a2e4-427a-b754-01acdf7d84b8","resolution":{"observed_at":"2026-07-13T16:08:30.031334Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.00632","last_updated":"2024-03-22T15:38:53Z","snapshot_observed_at":"2026-08-10T05:54:54.449070Z","submitted_at":"2023-10-01T10:06:01Z","title":"Win-Win: Training High-Resolution Vision Transformers from Two Windows","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.00632","snapshot_observed_at":"2026-07-13T16:08:30.031334Z","title":"Win- Win: Training high-resolution vision transformers from two windows.arXiv preprint arXiv:2310.00632, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2603.28759","last_updated":"2026-05-31T17:37:40Z","snapshot_observed_at":"2026-08-10T13:07:04.823949Z","submitted_at":"2026-03-30T17:58:12Z","title":"FlowIt: Global Matching via Hierarchical Transformers and Optimal Transport for Optical Flow","version":2},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-07-13T16:08:30.031334Z"},"links":{"cited_paper":"/paper/2310.00632","citing_paper":"/paper/2603.28759"},"observation_digest":"sha256:e6f7ad5bd4de2b25719ce3e10767bd83051cd9b1713c558e97ef1579757d033c","observation_id":"4ed1c9ff-d185-49f9-86d8-597ef93d5d9d","resolution":{"observed_at":"2026-07-13T16:08:30.031334Z","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":"2026-07-13T16:08:30.031334Z","title":"MegaDepth: Learning single-view depth prediction from internet photos","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2603.28759","last_updated":"2026-05-31T17:37:40Z","snapshot_observed_at":"2026-08-10T13:07:04.823949Z","submitted_at":"2026-03-30T17:58:12Z","title":"FlowIt: Global Matching via Hierarchical Transformers and Optimal Transport for Optical Flow","version":2},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-07-13T16:08:30.031334Z"},"links":{"citing_paper":"/paper/2603.28759"},"observation_digest":"sha256:5f6fec0f2abb24d60e44acfde37d711daf5c5269e500fd6827828a4231f86d75","observation_id":"ec9142ab-cc8b-4d96-bcc9-4e5d2f9c9a20","resolution":{"observed_at":"2026-07-13T16:08:30.031334Z","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":"2026-07-13T16:08:30.031334Z","title":"SIFT flow: Dense correspondence across scenes and its applications.IEEE TPAMI, 33(5):978–994, 2010","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2603.28759","last_updated":"2026-05-31T17:37:40Z","snapshot_observed_at":"2026-08-10T13:07:04.823949Z","submitted_at":"2026-03-30T17:58:12Z","title":"FlowIt: Global Matching via Hierarchical Transformers and Optimal Transport for Optical Flow","version":2},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-07-13T16:08:30.031334Z"},"links":{"citing_paper":"/paper/2603.28759"},"observation_digest":"sha256:43a6932b4d37a6b0f2ba771812f3b5ec326cbcc06424a01a602d1322a3eacef6","observation_id":"88924ddd-a059-4372-a033-66267cf68efa","resolution":{"observed_at":"2026-07-13T16:08:30.031334Z","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":"2026-07-13T16:08:30.031334Z","title":"ARFlow: Auto-regressive op- tical flow estimation for arbitrary-length videos via progressive next-frame forecasting","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2603.28759","last_updated":"2026-05-31T17:37:40Z","snapshot_observed_at":"2026-08-10T13:07:04.823949Z","submitted_at":"2026-03-30T17:58:12Z","title":"FlowIt: Global Matching via Hierarchical Transformers and Optimal Transport for Optical Flow","version":2},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-07-13T16:08:30.031334Z"},"links":{"citing_paper":"/paper/2603.28759"},"observation_digest":"sha256:2ec41447fa28d722515b206e9fb8f47a44a14c1148eb4a9da426f47ca29cddcc","observation_id":"567c9336-5d5b-43a0-83bf-e486fcae8c30","resolution":{"observed_at":"2026-07-13T16:08:30.031334Z","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":"2026-07-13T16:08:30.031334Z","title":"Learning by analogy: Reliable su- pervision from transformations for unsupervised optical flow estimation","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2603.28759","last_updated":"2026-05-31T17:37:40Z","snapshot_observed_at":"2026-08-10T13:07:04.823949Z","submitted_at":"2026-03-30T17:58:12Z","title":"FlowIt: Global Matching via Hierarchical Transformers and Optimal Transport for Optical Flow","version":2},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-07-13T16:08:30.031334Z"},"links":{"citing_paper":"/paper/2603.28759"},"observation_digest":"sha256:668b575a65997bc92ee5911dbcf3804c2b7ca8b8ed0ac15662a9fcffe659db3e","observation_id":"767008d8-fc6e-49cb-bfd9-cc7b0ca2fea6","resolution":{"observed_at":"2026-07-13T16:08:30.031334Z","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":"2026-07-13T16:08:30.031334Z","title":"Flow2Stereo: Effective self- supervised learning of optical flow and stereo matching","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2603.28759","last_updated":"2026-05-31T17:37:40Z","snapshot_observed_at":"2026-08-10T13:07:04.823949Z","submitted_at":"2026-03-30T17:58:12Z","title":"FlowIt: Global Matching via Hierarchical Transformers and Optimal Transport for Optical Flow","version":2},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-07-13T16:08:30.031334Z"},"links":{"citing_paper":"/paper/2603.28759"},"observation_digest":"sha256:048ed78c5c134c63afbdd371eb05675694d69cb7c9792e2a029bb5f437fdd15b","observation_id":"51cc41ea-c74e-437d-aa8e-4ccfb774aba2","resolution":{"observed_at":"2026-07-13T16:08:30.031334Z","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":"2026-07-13T16:08:30.031334Z","title":"Video frame interpolation via optical flow estimation with image inpainting.IJCV, 35(12):2087–2102, 2020","venue":null,"work_id":null,"year":2087},"citing_paper":{"arxiv_id":"2603.28759","last_updated":"2026-05-31T17:37:40Z","snapshot_observed_at":"2026-08-10T13:07:04.823949Z","submitted_at":"2026-03-30T17:58:12Z","title":"FlowIt: Global Matching via Hierarchical Transformers and Optimal Transport for Optical Flow","version":2},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-07-13T16:08:30.031334Z"},"links":{"citing_paper":"/paper/2603.28759"},"observation_digest":"sha256:75f3731be605460f23edb0303cc56859e69313718be52da5367fbc4a531f1f8a","observation_id":"f2c7f6ba-4f7a-4148-8cd4-0907ee2ab8d5","resolution":{"observed_at":"2026-07-13T16:08:30.031334Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1711.05101","last_updated":"2019-01-04T21:01:49Z","snapshot_observed_at":"2026-08-09T20:34:52.923500Z","submitted_at":"2017-11-14T14:24:06Z","title":"Decoupled Weight Decay Regularization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1711.05101","snapshot_observed_at":"2026-07-13T16:08:30.031334Z","title":"Decoupled weight decay regularization.arXiv preprint arXiv:1711.05101, 2017","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2603.28759","last_updated":"2026-05-31T17:37:40Z","snapshot_observed_at":"2026-08-10T13:07:04.823949Z","submitted_at":"2026-03-30T17:58:12Z","title":"FlowIt: Global Matching via Hierarchical Transformers and Optimal Transport for Optical Flow","version":2},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-07-13T16:08:30.031334Z"},"links":{"cited_paper":"/paper/1711.05101","citing_paper":"/paper/2603.28759"},"observation_digest":"sha256:36609bbb13e36a1bed948c2574ca41cb66820064e06ee7347b119f1c54260030","observation_id":"c341bdce-0760-41e4-bf8f-0c8f3dedae55","resolution":{"observed_at":"2026-07-13T16:08:30.031334Z","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":"2026-07-13T16:08:30.031334Z","title":"Learn- ing optical flow with adaptive graph reasoning","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2603.28759","last_updated":"2026-05-31T17:37:40Z","snapshot_observed_at":"2026-08-10T13:07:04.823949Z","submitted_at":"2026-03-30T17:58:12Z","title":"FlowIt: Global Matching via Hierarchical Transformers and Optimal Transport for Optical Flow","version":2},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-07-13T16:08:30.031334Z"},"links":{"citing_paper":"/paper/2603.28759"},"observation_digest":"sha256:113c8f27db29e181715b790aa32e6e38010738ad06f583ca23644406698c6e70","observation_id":"2596d95a-7ae5-40a1-81f8-a48238c73363","resolution":{"observed_at":"2026-07-13T16:08:30.031334Z","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":"2026-07-13T16:08:30.031334Z","title":"FlowDif- fuser: Advancing optical flow estimation with diffusion models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2603.28759","last_updated":"2026-05-31T17:37:40Z","snapshot_observed_at":"2026-08-10T13:07:04.823949Z","submitted_at":"2026-03-30T17:58:12Z","title":"FlowIt: Global Matching via Hierarchical Transformers and Optimal Transport for Optical Flow","version":2},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-07-13T16:08:30.031334Z"},"links":{"citing_paper":"/paper/2603.28759"},"observation_digest":"sha256:a97d712ca756d87e7e3fcbb029d0c31336e4f7c15ef1934fa3e7abd3072a9ad6","observation_id":"5c12ddbd-a14c-46c7-83fe-93bb8d99b8b1","resolution":{"observed_at":"2026-07-13T16:08:30.031334Z","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":"2026-07-13T16:08:30.031334Z","title":"A large dataset to train convolutional networks for disparity, optical flow, and scene flow estimation","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2603.28759","last_updated":"2026-05-31T17:37:40Z","snapshot_observed_at":"2026-08-10T13:07:04.823949Z","submitted_at":"2026-03-30T17:58:12Z","title":"FlowIt: Global Matching via Hierarchical Transformers and Optimal Transport for Optical Flow","version":2},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-07-13T16:08:30.031334Z"},"links":{"citing_paper":"/paper/2603.28759"},"observation_digest":"sha256:0db8e54db72b926061e505d6d704e727a368c449657dd55de5a8da60be83d577","observation_id":"e8aeca86-e4fe-400e-baee-05e0b55ee02f","resolution":{"observed_at":"2026-07-13T16:08:30.031334Z","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":"2026-07-13T16:08:30.031334Z","title":"Spring: A high-resolution high-detail dataset and benchmark for scene flow, optical flow and stereo","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2603.28759","last_updated":"2026-05-31T17:37:40Z","snapshot_observed_at":"2026-08-10T13:07:04.823949Z","submitted_at":"2026-03-30T17:58:12Z","title":"FlowIt: Global Matching via Hierarchical Transformers and Optimal Transport for Optical Flow","version":2},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-07-13T16:08:30.031334Z"},"links":{"citing_paper":"/paper/2603.28759"},"observation_digest":"sha256:a71339fff8ee53d620f54783a08e95ec0b9bac355f936e180692fbd203e75ae7","observation_id":"a1db3777-9604-4102-950b-0df5e8c8a4c5","resolution":{"observed_at":"2026-07-13T16:08:30.031334Z","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":"2026-07-13T16:08:30.031334Z","title":"Object scene flow for autonomous vehicles","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2603.28759","last_updated":"2026-05-31T17:37:40Z","snapshot_observed_at":"2026-08-10T13:07:04.823949Z","submitted_at":"2026-03-30T17:58:12Z","title":"FlowIt: Global Matching via Hierarchical Transformers and Optimal Transport for Optical Flow","version":2},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-07-13T16:08:30.031334Z"},"links":{"citing_paper":"/paper/2603.28759"},"observation_digest":"sha256:ea03302b08716d6102c5e010ad4fdc7c399c197d016320d369569be04a4ec89a","observation_id":"befac680-8c1d-4c0f-88a3-36a5b174b06a","resolution":{"observed_at":"2026-07-13T16:08:30.031334Z","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":"2026-07-13T16:08:30.031334Z","title":"Confidence aware stereo matching for realistic clut- tered scenario","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2603.28759","last_updated":"2026-05-31T17:37:40Z","snapshot_observed_at":"2026-08-10T13:07:04.823949Z","submitted_at":"2026-03-30T17:58:12Z","title":"FlowIt: Global Matching via Hierarchical Transformers and Optimal Transport for Optical Flow","version":2},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-07-13T16:08:30.031334Z"},"links":{"citing_paper":"/paper/2603.28759"},"observation_digest":"sha256:68c0d4f9b22194975d1c24aacf35009eed8e6ea26df1f1d51a22fa161bdc9e3f","observation_id":"db9a4539-db99-45b4-a902-b25e0eb75be7","resolution":{"observed_at":"2026-07-13T16:08:30.031334Z","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":"2026-07-13T16:08:30.031334Z","title":"S2M2: Scalable stereo matching model for reliable depth estimation","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2603.28759","last_updated":"2026-05-31T17:37:40Z","snapshot_observed_at":"2026-08-10T13:07:04.823949Z","submitted_at":"2026-03-30T17:58:12Z","title":"FlowIt: Global Matching via Hierarchical Transformers and Optimal Transport for Optical Flow","version":2},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-07-13T16:08:30.031334Z"},"links":{"citing_paper":"/paper/2603.28759"},"observation_digest":"sha256:0fa72a2d9effe55f269c7ee323939f18d03ce89fb48949bb9853661180af5a4a","observation_id":"bcec8015-59be-4a55-966e-493afa7a3ef5","resolution":{"observed_at":"2026-07-13T16:08:30.031334Z","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":"2026-07-13T16:08:30.031334Z","title":"Recurrent partial kernel network for efficient optical flow estimation","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2603.28759","last_updated":"2026-05-31T17:37:40Z","snapshot_observed_at":"2026-08-10T13:07:04.823949Z","submitted_at":"2026-03-30T17:58:12Z","title":"FlowIt: Global Matching via Hierarchical Transformers and Optimal Transport for Optical Flow","version":2},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-07-13T16:08:30.031334Z"},"links":{"citing_paper":"/paper/2603.28759"},"observation_digest":"sha256:3a222e5a4b3749453e57e3d451c5760b44cc1288337d3e37f026b4efecb2bfd0","observation_id":"710c66f9-c99c-40e6-9c13-4f80c5298fd6","resolution":{"observed_at":"2026-07-13T16:08:30.031334Z","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":"2026-07-13T16:08:30.031334Z","title":"DPFlow: Adaptive optical flow estimation with a dual-pyramid framework.arXiv preprint arXiv:2503.14880, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2603.28759","last_updated":"2026-05-31T17:37:40Z","snapshot_observed_at":"2026-08-10T13:07:04.823949Z","submitted_at":"2026-03-30T17:58:12Z","title":"FlowIt: Global Matching via Hierarchical Transformers and Optimal Transport for Optical Flow","version":2},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-07-13T16:08:30.031334Z"},"links":{"citing_paper":"/paper/2603.28759"},"observation_digest":"sha256:9017fc4a1f02ed2b74d1b4831c07f4fb1630c78803834c6c5ec29c9db4740d05","observation_id":"6b69281f-072b-4aff-bc9e-9c00552fc647","resolution":{"observed_at":"2026-07-13T16:08:30.031334Z","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":"2026-07-13T16:08:30.031334Z","title":"Automatic differentiation in PyTorch","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2603.28759","last_updated":"2026-05-31T17:37:40Z","snapshot_observed_at":"2026-08-10T13:07:04.823949Z","submitted_at":"2026-03-30T17:58:12Z","title":"FlowIt: Global Matching via Hierarchical Transformers and Optimal Transport for Optical Flow","version":2},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-07-13T16:08:30.031334Z"},"links":{"citing_paper":"/paper/2603.28759"},"observation_digest":"sha256:23b62cf7fc1af1241504ca84a61c0e0267b0501d33a4be1f183fb735b7fe067a","observation_id":"ee45b440-431f-449e-9770-4cab1230b93f","resolution":{"observed_at":"2026-07-13T16:08:30.031334Z","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":"2026-07-13T16:08:30.031334Z","title":"Representation flow for action recognition","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2603.28759","last_updated":"2026-05-31T17:37:40Z","snapshot_observed_at":"2026-08-10T13:07:04.823949Z","submitted_at":"2026-03-30T17:58:12Z","title":"FlowIt: Global Matching via Hierarchical Transformers and Optimal Transport for Optical Flow","version":2},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-07-13T16:08:30.031334Z"},"links":{"citing_paper":"/paper/2603.28759"},"observation_digest":"sha256:6620ffc28836b6c99e1fc08abb18819bf2b12e7bb591996ef04fef457083bdb8","observation_id":"4c7a608f-8988-46f5-8ca9-b6751ca2706f","resolution":{"observed_at":"2026-07-13T16:08:30.031334Z","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":"2026-07-13T16:08:30.031334Z","title":"FlowSeek: Optical flow made easier with depth founda- tion models and motion bases","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2603.28759","last_updated":"2026-05-31T17:37:40Z","snapshot_observed_at":"2026-08-10T13:07:04.823949Z","submitted_at":"2026-03-30T17:58:12Z","title":"FlowIt: Global Matching via Hierarchical Transformers and Optimal Transport for Optical Flow","version":2},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-07-13T16:08:30.031334Z"},"links":{"citing_paper":"/paper/2603.28759"},"observation_digest":"sha256:19985a65c37dd53bd9e5bd97e331128bf08b8af1073c2be616eff469b478785e","observation_id":"21974c1f-a50b-4080-956b-8e178119158d","resolution":{"observed_at":"2026-07-13T16:08:30.031334Z","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":"2026-07-13T16:08:30.031334Z","title":"Optical flow estimation using a spatial pyramid network","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2603.28759","last_updated":"2026-05-31T17:37:40Z","snapshot_observed_at":"2026-08-10T13:07:04.823949Z","submitted_at":"2026-03-30T17:58:12Z","title":"FlowIt: Global Matching via Hierarchical Transformers and Optimal Transport for Optical Flow","version":2},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-07-13T16:08:30.031334Z"},"links":{"citing_paper":"/paper/2603.28759"},"observation_digest":"sha256:a14dbd3bff1220adcbb3db65752f89d9bb3415e82d1e6da5a078712a16112035","observation_id":"d559bd79-bcc3-425a-b91b-7a6439e1ea56","resolution":{"observed_at":"2026-07-13T16:08:30.031334Z","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":"2026-07-13T16:08:30.031334Z","title":"Playing for benchmarks","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2603.28759","last_updated":"2026-05-31T17:37:40Z","snapshot_observed_at":"2026-08-10T13:07:04.823949Z","submitted_at":"2026-03-30T17:58:12Z","title":"FlowIt: Global Matching via Hierarchical Transformers and Optimal Transport for Optical Flow","version":2},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-07-13T16:08:30.031334Z"},"links":{"citing_paper":"/paper/2603.28759"},"observation_digest":"sha256:4040d9df06ee73da445097944d7f5f3a8b2d19492c24632df529cf17b980c801","observation_id":"52b9fa15-72bb-4133-b630-e4ec513a2260","resolution":{"observed_at":"2026-07-13T16:08:30.031334Z","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":"2026-07-13T16:08:30.031334Z","title":"SuperGlue: Learning feature matching with graph neural networks","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2603.28759","last_updated":"2026-05-31T17:37:40Z","snapshot_observed_at":"2026-08-10T13:07:04.823949Z","submitted_at":"2026-03-30T17:58:12Z","title":"FlowIt: Global Matching via Hierarchical Transformers and Optimal Transport for Optical Flow","version":2},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-07-13T16:08:30.031334Z"},"links":{"citing_paper":"/paper/2603.28759"},"observation_digest":"sha256:20d4bb362baa4f8ba500b29b0f4d88c0de87e9de44f4cb2bd8ee3265d11c0ff5","observation_id":"6889bce6-dbdd-4c12-93f7-dd7a518f37aa","resolution":{"observed_at":"2026-07-13T16:08:30.031334Z","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":"2026-07-13T16:08:30.031334Z","title":"The surprising effectiveness of diffusion models for optical flow and monocular depth estimation","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2603.28759","last_updated":"2026-05-31T17:37:40Z","snapshot_observed_at":"2026-08-10T13:07:04.823949Z","submitted_at":"2026-03-30T17:58:12Z","title":"FlowIt: Global Matching via Hierarchical Transformers and Optimal Transport for Optical Flow","version":2},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-07-13T16:08:30.031334Z"},"links":{"citing_paper":"/paper/2603.28759"},"observation_digest":"sha256:6551940295ecc0c744173dc85c50abc09893ec40260a787cea71526fa06519f3","observation_id":"5f60ca40-0545-4d62-a049-d5f7b69a85ac","resolution":{"observed_at":"2026-07-13T16:08:30.031334Z","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":"2026-07-13T16:08:30.031334Z","title":"VideoFlow: Ex- ploiting temporal cues for multi-frame optical flow estimation","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2603.28759","last_updated":"2026-05-31T17:37:40Z","snapshot_observed_at":"2026-08-10T13:07:04.823949Z","submitted_at":"2026-03-30T17:58:12Z","title":"FlowIt: Global Matching via Hierarchical Transformers and Optimal Transport for Optical Flow","version":2},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-07-13T16:08:30.031334Z"},"links":{"citing_paper":"/paper/2603.28759"},"observation_digest":"sha256:bf31e1788c2c03ce48905ade6dc9ea69fbd6c94418718ab01cf23713719afd47","observation_id":"e45832be-3b08-4158-8089-b24fc169c540","resolution":{"observed_at":"2026-07-13T16:08:30.031334Z","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":"2026-07-13T16:08:30.031334Z","title":"Flowformer++: Masked cost volume autoencoding for pretraining optical flow estimation","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2603.28759","last_updated":"2026-05-31T17:37:40Z","snapshot_observed_at":"2026-08-10T13:07:04.823949Z","submitted_at":"2026-03-30T17:58:12Z","title":"FlowIt: Global Matching via Hierarchical Transformers and Optimal Transport for Optical Flow","version":2},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-07-13T16:08:30.031334Z"},"links":{"citing_paper":"/paper/2603.28759"},"observation_digest":"sha256:35dcc9ad55bec138567e0495d9a615f01a67e1f7bf1a23f5a5294e2da1349d83","observation_id":"ffc24b79-19d6-4ac0-b670-bba0af576dda","resolution":{"observed_at":"2026-07-13T16:08:30.031334Z","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":"2026-07-13T16:08:30.031334Z","title":"Super-convergence: Very fast training of neural networks using large learning rates","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2603.28759","last_updated":"2026-05-31T17:37:40Z","snapshot_observed_at":"2026-08-10T13:07:04.823949Z","submitted_at":"2026-03-30T17:58:12Z","title":"FlowIt: Global Matching via Hierarchical Transformers and Optimal Transport for Optical Flow","version":2},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-07-13T16:08:30.031334Z"},"links":{"citing_paper":"/paper/2603.28759"},"observation_digest":"sha256:b1884a97d204d5d677e212a08cdfb1804ab460261aa0c8498d989a42fe38f035","observation_id":"4aadf461-cce4-4a74-bf8b-ef438d28804a","resolution":{"observed_at":"2026-07-13T16:08:30.031334Z","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":"2026-07-13T16:08:30.031334Z","title":"CRAFT: Cross-attentional flow transformer for robust optical flow","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2603.28759","last_updated":"2026-05-31T17:37:40Z","snapshot_observed_at":"2026-08-10T13:07:04.823949Z","submitted_at":"2026-03-30T17:58:12Z","title":"FlowIt: Global Matching via Hierarchical Transformers and Optimal Transport for Optical Flow","version":2},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-07-13T16:08:30.031334Z"},"links":{"citing_paper":"/paper/2603.28759"},"observation_digest":"sha256:a3465fd82de66767ddd7f86920d3166f3655ff52948f0e390b3e89f43af4636b","observation_id":"7a3351cc-6682-4df4-886f-f88042793165","resolution":{"observed_at":"2026-07-13T16:08:30.031334Z","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":"2026-07-13T16:08:30.031334Z","title":"PWC-Net: CNNs for optical flow using pyramid, warping, and cost volume","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2603.28759","last_updated":"2026-05-31T17:37:40Z","snapshot_observed_at":"2026-08-10T13:07:04.823949Z","submitted_at":"2026-03-30T17:58:12Z","title":"FlowIt: Global Matching via Hierarchical Transformers and Optimal Transport for Optical Flow","version":2},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-07-13T16:08:30.031334Z"},"links":{"citing_paper":"/paper/2603.28759"},"observation_digest":"sha256:305d4a9452be713937d47ea5fa7831f9f93c6224ad669d2feee0dabee2e67e4b","observation_id":"de53c83b-afbd-4708-b0f9-138dfd1195cf","resolution":{"observed_at":"2026-07-13T16:08:30.031334Z","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":"2026-07-13T16:08:30.031334Z","title":"Models matter, so does training: An empirical study of CNNs for optical flow estimation.IEEE TPAMI, 42(6): 1408–1423, 2019","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2603.28759","last_updated":"2026-05-31T17:37:40Z","snapshot_observed_at":"2026-08-10T13:07:04.823949Z","submitted_at":"2026-03-30T17:58:12Z","title":"FlowIt: Global Matching via Hierarchical Transformers and Optimal Transport for Optical Flow","version":2},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-07-13T16:08:30.031334Z"},"links":{"citing_paper":"/paper/2603.28759"},"observation_digest":"sha256:5cb1653a2012c57bbc65e51222acead3f5fa00990316b86d67ae3814e2a84e7e","observation_id":"009f214d-d3de-4a85-80f5-b0fa42f8431f","resolution":{"observed_at":"2026-07-13T16:08:30.031334Z","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":"2026-07-13T16:08:30.031334Z","title":"AutoFlow: Learning a better training set for optical flow","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2603.28759","last_updated":"2026-05-31T17:37:40Z","snapshot_observed_at":"2026-08-10T13:07:04.823949Z","submitted_at":"2026-03-30T17:58:12Z","title":"FlowIt: Global Matching via Hierarchical Transformers and Optimal Transport for Optical Flow","version":2},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-07-13T16:08:30.031334Z"},"links":{"citing_paper":"/paper/2603.28759"},"observation_digest":"sha256:c69573a80eb4692964cb418f4fd24e31d67a08812dbf8cec1fc068298a77279b","observation_id":"7533243d-facf-4d95-8d2f-2bf61f73bc65","resolution":{"observed_at":"2026-07-13T16:08:30.031334Z","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":"2026-07-13T16:08:30.031334Z","title":"Disentangling architecture and training for optical flow","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2603.28759","last_updated":"2026-05-31T17:37:40Z","snapshot_observed_at":"2026-08-10T13:07:04.823949Z","submitted_at":"2026-03-30T17:58:12Z","title":"FlowIt: Global Matching via Hierarchical Transformers and Optimal Transport for Optical Flow","version":2},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-07-13T16:08:30.031334Z"},"links":{"citing_paper":"/paper/2603.28759"},"observation_digest":"sha256:355fc902f57953aaec986f811519b30ad42607093062c3dcd4964e2a6343c997","observation_id":"2c451a41-41ec-415f-9c0d-68ed7cd30a9d","resolution":{"observed_at":"2026-07-13T16:08:30.031334Z","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":"2026-07-13T16:08:30.031334Z","title":"SKFlow: Learning optical flow with super kernels","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2603.28759","last_updated":"2026-05-31T17:37:40Z","snapshot_observed_at":"2026-08-10T13:07:04.823949Z","submitted_at":"2026-03-30T17:58:12Z","title":"FlowIt: Global Matching via Hierarchical Transformers and Optimal Transport for Optical Flow","version":2},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-07-13T16:08:30.031334Z"},"links":{"citing_paper":"/paper/2603.28759"},"observation_digest":"sha256:19aff35eea31586b015352de64de43dd79e34dd6348d9edfbacb4de2f1f65742","observation_id":"54e69830-e4b2-4aa6-9978-fcfce81a0f53","resolution":{"observed_at":"2026-07-13T16:08:30.031334Z","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":"2026-07-13T16:08:30.031334Z","title":"Streamflow: streamlined multi-frame optical flow estimation for video sequences.Ad- vances in neural information processing systems, 37:9205–9228, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2603.28759","last_updated":"2026-05-31T17:37:40Z","snapshot_observed_at":"2026-08-10T13:07:04.823949Z","submitted_at":"2026-03-30T17:58:12Z","title":"FlowIt: Global Matching via Hierarchical Transformers and Optimal Transport for Optical Flow","version":2},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-07-13T16:08:30.031334Z"},"links":{"citing_paper":"/paper/2603.28759"},"observation_digest":"sha256:95c14124eb4d4194e4314b3d4b0e28e31d2b2332e385e6de380b989f31de2936","observation_id":"6bc63d98-678b-48cd-91e9-ae1be503c9e9","resolution":{"observed_at":"2026-07-13T16:08:30.031334Z","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":"2026-07-13T16:08:30.031334Z","title":"Optical flow guided feature: A fast and robust motion representation for video action recogni- tion","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2603.28759","last_updated":"2026-05-31T17:37:40Z","snapshot_observed_at":"2026-08-10T13:07:04.823949Z","submitted_at":"2026-03-30T17:58:12Z","title":"FlowIt: Global Matching via Hierarchical Transformers and Optimal Transport for Optical Flow","version":2},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-07-13T16:08:30.031334Z"},"links":{"citing_paper":"/paper/2603.28759"},"observation_digest":"sha256:02c227eb8627f16345c584f10fa7295417703fbb6fd63e7ad27e239b4754a777","observation_id":"4d3146c9-4053-4073-8a97-c92513f5c344","resolution":{"observed_at":"2026-07-13T16:08:30.031334Z","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":"2026-07-13T16:08:30.031334Z","title":"RAFT: Recurrent all-pairs field transforms for optical flow","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2603.28759","last_updated":"2026-05-31T17:37:40Z","snapshot_observed_at":"2026-08-10T13:07:04.823949Z","submitted_at":"2026-03-30T17:58:12Z","title":"FlowIt: Global Matching via Hierarchical Transformers and Optimal Transport for Optical Flow","version":2},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-07-13T16:08:30.031334Z"},"links":{"citing_paper":"/paper/2603.28759"},"observation_digest":"sha256:2bcabc62a59aefdfa29f85724ebd00886df12ce591cc5f843c2f235f6d650618","observation_id":"b3087bc8-f233-4abf-8565-7e7cf2e6e13a","resolution":{"observed_at":"2026-07-13T16:08:30.031334Z","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":"2026-07-13T16:08:30.031334Z","title":"Splatflow: Learning multi-frame optical flow via splatting.International Journal of Computer Vision, 132(8):3023–3045, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2603.28759","last_updated":"2026-05-31T17:37:40Z","snapshot_observed_at":"2026-08-10T13:07:04.823949Z","submitted_at":"2026-03-30T17:58:12Z","title":"FlowIt: Global Matching via Hierarchical Transformers and Optimal Transport for Optical Flow","version":2},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-07-13T16:08:30.031334Z"},"links":{"citing_paper":"/paper/2603.28759"},"observation_digest":"sha256:16e428e636bda5748c5276d188823de9445d0e7ab6fbe55ff5a624ae06a1bfe3","observation_id":"10aa021e-4ad9-4a61-90c3-d5b30e33f549","resolution":{"observed_at":"2026-07-13T16:08:30.031334Z","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":"2026-07-13T16:08:30.031334Z","title":"TartanAir: A dataset to push the limits of visual SLAM","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2603.28759","last_updated":"2026-05-31T17:37:40Z","snapshot_observed_at":"2026-08-10T13:07:04.823949Z","submitted_at":"2026-03-30T17:58:12Z","title":"FlowIt: Global Matching via Hierarchical Transformers and Optimal Transport for Optical Flow","version":2},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-07-13T16:08:30.031334Z"},"links":{"citing_paper":"/paper/2603.28759"},"observation_digest":"sha256:6150dd2339a43963df76365f07cc1866f12c55c5f4a262053e7a4591c28ca2bd","observation_id":"eb807586-f651-4740-b4db-8624e40a727a","resolution":{"observed_at":"2026-07-13T16:08:30.031334Z","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":"2026-07-13T16:08:30.031334Z","title":"W AFT: Warping-alone field transforms for optical flow","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2603.28759","last_updated":"2026-05-31T17:37:40Z","snapshot_observed_at":"2026-08-10T13:07:04.823949Z","submitted_at":"2026-03-30T17:58:12Z","title":"FlowIt: Global Matching via Hierarchical Transformers and Optimal Transport for Optical Flow","version":2},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-07-13T16:08:30.031334Z"},"links":{"citing_paper":"/paper/2603.28759"},"observation_digest":"sha256:831341645b3901fc61014d01a921e47e529c17677f78bcf710d6ce16f6d03456","observation_id":"37177a57-c2fa-4b59-96a7-1f00dd06faf8","resolution":{"observed_at":"2026-07-13T16:08:30.031334Z","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":"2026-07-13T16:08:30.031334Z","title":"SEA-RAFT: Simple, efficient, accurate RAFT for optical flow","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2603.28759","last_updated":"2026-05-31T17:37:40Z","snapshot_observed_at":"2026-08-10T13:07:04.823949Z","submitted_at":"2026-03-30T17:58:12Z","title":"FlowIt: Global Matching via Hierarchical Transformers and Optimal Transport for Optical Flow","version":2},"reference_index":73,"source":"pdf_text","source_observed_at":"2026-07-13T16:08:30.031334Z"},"links":{"citing_paper":"/paper/2603.28759"},"observation_digest":"sha256:bdae7b9d5d190bd3f09e638aeb9f3e2db99745dcb30a38892250ab990821d50d","observation_id":"7d469b24-1dee-4eb8-bed6-e6766af95292","resolution":{"observed_at":"2026-07-13T16:08:30.031334Z","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":"2026-07-13T16:08:30.031334Z","title":"CroCo v2: Improved cross-view completion pre-training for stereo matching and optical flow","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2603.28759","last_updated":"2026-05-31T17:37:40Z","snapshot_observed_at":"2026-08-10T13:07:04.823949Z","submitted_at":"2026-03-30T17:58:12Z","title":"FlowIt: Global Matching via Hierarchical Transformers and Optimal Transport for Optical Flow","version":2},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-07-13T16:08:30.031334Z"},"links":{"citing_paper":"/paper/2603.28759"},"observation_digest":"sha256:37c51730f7c1003aa8cad20671882469d700371a4b47e323435e881461cadae7","observation_id":"778cd0a5-e72c-4e36-adaf-4b773891177d","resolution":{"observed_at":"2026-07-13T16:08:30.031334Z","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":"2026-07-13T16:08:30.031334Z","title":"Layeredflow: A real-world benchmark for non-lambertian multi-layer optical flow","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2603.28759","last_updated":"2026-05-31T17:37:40Z","snapshot_observed_at":"2026-08-10T13:07:04.823949Z","submitted_at":"2026-03-30T17:58:12Z","title":"FlowIt: Global Matching via Hierarchical Transformers and Optimal Transport for Optical Flow","version":2},"reference_index":75,"source":"pdf_text","source_observed_at":"2026-07-13T16:08:30.031334Z"},"links":{"citing_paper":"/paper/2603.28759"},"observation_digest":"sha256:2fdd5a548eb6f1abd805b286fc00c2c823248b91ca9539d91cbd0f79b07a0694","observation_id":"5e1e4ee5-55d9-44df-aa6e-9373f25acfed","resolution":{"observed_at":"2026-07-13T16:08:30.031334Z","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":"2026-07-13T16:08:30.031334Z","title":"GMFlow: Learning optical flow via global matching","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2603.28759","last_updated":"2026-05-31T17:37:40Z","snapshot_observed_at":"2026-08-10T13:07:04.823949Z","submitted_at":"2026-03-30T17:58:12Z","title":"FlowIt: Global Matching via Hierarchical Transformers and Optimal Transport for Optical Flow","version":2},"reference_index":76,"source":"pdf_text","source_observed_at":"2026-07-13T16:08:30.031334Z"},"links":{"citing_paper":"/paper/2603.28759"},"observation_digest":"sha256:c7507f748af871e864c04700468d3af9c452a025dc9e69a2c067b605879986b5","observation_id":"9393183a-c39c-4745-8c23-18d4048b82e6","resolution":{"observed_at":"2026-07-13T16:08:30.031334Z","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":"2026-07-13T16:08:30.031334Z","title":"Unifying flow, stereo and depth estimation.IEEE TPAMI, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2603.28759","last_updated":"2026-05-31T17:37:40Z","snapshot_observed_at":"2026-08-10T13:07:04.823949Z","submitted_at":"2026-03-30T17:58:12Z","title":"FlowIt: Global Matching via Hierarchical Transformers and Optimal Transport for Optical Flow","version":2},"reference_index":77,"source":"pdf_text","source_observed_at":"2026-07-13T16:08:30.031334Z"},"links":{"citing_paper":"/paper/2603.28759"},"observation_digest":"sha256:5dd8d5c6b4e12a1b5c1b1d319be71f2f4ffedef97739aba3aef6d9be5e642773","observation_id":"bffa221a-3212-4e84-945e-75077282739d","resolution":{"observed_at":"2026-07-13T16:08:30.031334Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1809.03327","last_updated":"2018-09-06T04:19:45Z","snapshot_observed_at":"2026-07-06T07:00:12.122241Z","submitted_at":"2018-09-06T04:19:45Z","title":"YouTube-VOS: A Large-Scale Video Object Segmentation Benchmark","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1809.03327","snapshot_observed_at":"2026-07-13T16:08:30.031334Z","title":"Youtube-VOS: A large-scale video object segmentation benchmark","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2603.28759","last_updated":"2026-05-31T17:37:40Z","snapshot_observed_at":"2026-08-10T13:07:04.823949Z","submitted_at":"2026-03-30T17:58:12Z","title":"FlowIt: Global Matching via Hierarchical Transformers and Optimal Transport for Optical Flow","version":2},"reference_index":78,"source":"pdf_text","source_observed_at":"2026-07-13T16:08:30.031334Z"},"links":{"cited_paper":"/paper/1809.03327","citing_paper":"/paper/2603.28759"},"observation_digest":"sha256:c52880e4d4eaf4a418242e8a0ff2a0b9152525e1c52a0ed3a48a65d120b57632","observation_id":"5d7c2b68-6663-4bd6-9907-afd4a0d487fc","resolution":{"observed_at":"2026-07-13T16:08:30.031334Z","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":"2026-07-13T16:08:30.031334Z","title":"Deep flow-guided video inpainting","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2603.28759","last_updated":"2026-05-31T17:37:40Z","snapshot_observed_at":"2026-08-10T13:07:04.823949Z","submitted_at":"2026-03-30T17:58:12Z","title":"FlowIt: Global Matching via Hierarchical Transformers and Optimal Transport for Optical Flow","version":2},"reference_index":79,"source":"pdf_text","source_observed_at":"2026-07-13T16:08:30.031334Z"},"links":{"citing_paper":"/paper/2603.28759"},"observation_digest":"sha256:3e985bcf6f04458a5fdf46910a4d478f4a2190183b8a07b7bf89e07d9f711de2","observation_id":"bd4740dc-8e98-4b83-a2b5-94ce50265aaa","resolution":{"observed_at":"2026-07-13T16:08:30.031334Z","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":"2026-07-13T16:08:30.031334Z","title":"Quadratic video interpolation","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2603.28759","last_updated":"2026-05-31T17:37:40Z","snapshot_observed_at":"2026-08-10T13:07:04.823949Z","submitted_at":"2026-03-30T17:58:12Z","title":"FlowIt: Global Matching via Hierarchical Transformers and Optimal Transport for Optical Flow","version":2},"reference_index":80,"source":"pdf_text","source_observed_at":"2026-07-13T16:08:30.031334Z"},"links":{"citing_paper":"/paper/2603.28759"},"observation_digest":"sha256:5b9f4d89eed2d79636816a07c4ec9e86c8c0276910b90ba436efb063f4fe7dea","observation_id":"ad063178-31d9-4642-b4d2-10e708bb727b","resolution":{"observed_at":"2026-07-13T16:08:30.031334Z","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":"2026-07-13T16:08:30.031334Z","title":"V olumetric correspondence networks for optical flow","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2603.28759","last_updated":"2026-05-31T17:37:40Z","snapshot_observed_at":"2026-08-10T13:07:04.823949Z","submitted_at":"2026-03-30T17:58:12Z","title":"FlowIt: Global Matching via Hierarchical Transformers and Optimal Transport for Optical Flow","version":2},"reference_index":81,"source":"pdf_text","source_observed_at":"2026-07-13T16:08:30.031334Z"},"links":{"citing_paper":"/paper/2603.28759"},"observation_digest":"sha256:920725baceea8fe99e11b7694b69bef77a855dbb94061847d40b7b5c1835c1cc","observation_id":"445d7e5a-9fac-45f8-a34b-1f03a8907a94","resolution":{"observed_at":"2026-07-13T16:08:30.031334Z","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":"2026-07-13T16:08:30.031334Z","title":"A duality based approach for realtime tv-l1 optical flow","venue":null,"work_id":null,"year":2007},"citing_paper":{"arxiv_id":"2603.28759","last_updated":"2026-05-31T17:37:40Z","snapshot_observed_at":"2026-08-10T13:07:04.823949Z","submitted_at":"2026-03-30T17:58:12Z","title":"FlowIt: Global Matching via Hierarchical Transformers and Optimal Transport for Optical Flow","version":2},"reference_index":82,"source":"pdf_text","source_observed_at":"2026-07-13T16:08:30.031334Z"},"links":{"citing_paper":"/paper/2603.28759"},"observation_digest":"sha256:9ba992254f59ef9278eb63f340fe9cc239b1493867865ba7e63c38e882a86121","observation_id":"a7bc4272-7a4f-46f8-a20e-4ea94a84f245","resolution":{"observed_at":"2026-07-13T16:08:30.031334Z","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":"2026-07-13T16:08:30.031334Z","title":"Global matching with overlapping attention for optical flow estimation","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2603.28759","last_updated":"2026-05-31T17:37:40Z","snapshot_observed_at":"2026-08-10T13:07:04.823949Z","submitted_at":"2026-03-30T17:58:12Z","title":"FlowIt: Global Matching via Hierarchical Transformers and Optimal Transport for Optical Flow","version":2},"reference_index":83,"source":"pdf_text","source_observed_at":"2026-07-13T16:08:30.031334Z"},"links":{"citing_paper":"/paper/2603.28759"},"observation_digest":"sha256:dd1b0190ca79298bba6a57c67842119ddffb86f1c876734d189f8476ec8cc374","observation_id":"d490d5a6-9706-4558-af6a-8b6d4b9fb5a5","resolution":{"observed_at":"2026-07-13T16:08:30.031334Z","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":"2026-07-13T16:08:30.031334Z","title":"Improved two-stream model for human action recognition.EURASIP Journal on Image and Video Processing, 2020(1):1–9, 2020","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2603.28759","last_updated":"2026-05-31T17:37:40Z","snapshot_observed_at":"2026-08-10T13:07:04.823949Z","submitted_at":"2026-03-30T17:58:12Z","title":"FlowIt: Global Matching via Hierarchical Transformers and Optimal Transport for Optical Flow","version":2},"reference_index":84,"source":"pdf_text","source_observed_at":"2026-07-13T16:08:30.031334Z"},"links":{"citing_paper":"/paper/2603.28759"},"observation_digest":"sha256:c380031e5d35160da38dc617f944c5c6252bd5fe01063412ecfd30fa9a0e75dd","observation_id":"4cf42b7b-47ba-4af6-87b2-8e45f096b0f5","resolution":{"observed_at":"2026-07-13T16:08:30.031334Z","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":"2026-07-13T16:08:30.031334Z","title":"DIP: Deep inverse patchmatch for high-resolution optical flow","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2603.28759","last_updated":"2026-05-31T17:37:40Z","snapshot_observed_at":"2026-08-10T13:07:04.823949Z","submitted_at":"2026-03-30T17:58:12Z","title":"FlowIt: Global Matching via Hierarchical Transformers and Optimal Transport for Optical Flow","version":2},"reference_index":85,"source":"pdf_text","source_observed_at":"2026-07-13T16:08:30.031334Z"},"links":{"citing_paper":"/paper/2603.28759"},"observation_digest":"sha256:681ae0a2d9e9ef2e4775f67f428e21492be982fe82fccf692bf0473a9a883a44","observation_id":"3a5b10b2-9bbc-4633-895b-f77bec139729","resolution":{"observed_at":"2026-07-13T16:08:30.031334Z","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":"2026-07-13T16:08:30.031334Z","title":"SamFlow: Eliminating any fragmen- tation in optical flow with segment anything model","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2603.28759","last_updated":"2026-05-31T17:37:40Z","snapshot_observed_at":"2026-08-10T13:07:04.823949Z","submitted_at":"2026-03-30T17:58:12Z","title":"FlowIt: Global Matching via Hierarchical Transformers and Optimal Transport for Optical Flow","version":2},"reference_index":86,"source":"pdf_text","source_observed_at":"2026-07-13T16:08:30.031334Z"},"links":{"citing_paper":"/paper/2603.28759"},"observation_digest":"sha256:5e5743fd697c5ec055b02b61d974ac5ec823983ca8dc39950d54bb181704d1bd","observation_id":"a38c2f04-abbc-460b-a5d3-d4f4098088a7","resolution":{"observed_at":"2026-07-13T16:08:30.031334Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2603.28759","last_updated":"2026-05-31T17:37:40Z","latest_version":2,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-10T13:07:04.823949Z","submitted_at":"2026-03-30T17:58:12Z","title":"FlowIt: Global Matching via Hierarchical Transformers and Optimal Transport for Optical Flow"},"reference_resolution":{"displayed":86,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":86,"verified_exact":0,"verified_fuzzy":0},"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":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 86 of 86 outbound references and 0 inbound Pith citation observations for arXiv:2603.28759."}