{"as_of":"2026-08-10T23:06:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:0795320bcad58a1a1593c733b2656bf84325c1c4de549745c0b027c87ff10ee9","coverage":[{"denominator":74,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":74,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-09T12:53:45.993773Z","state":"measured"},{"denominator":75,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":75,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-10T06:31:04.303077+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-05-18T16:28:48.494939Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-05-18T16:31:37.163858Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2502.02257","last_updated":"2025-03-20T13:55:08Z","snapshot_observed_at":"2026-08-10T12:43:23.653091Z","submitted_at":"2025-02-04T12:08:20Z","title":"UNIP: Rethinking Pre-trained Attention Patterns for Infrared Semantic Segmentation","version":2},"cited_work":{"arxiv_id":"2502.02257","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2502.02257","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Unip: Rethinking pre-trained attention patterns for infrared semantic segmentation","venue":null,"work_id":"3228c784-9cc7-4f0c-84b2-1654a70527f8","year":2025},"citing_paper":{"arxiv_id":"2509.15642","last_updated":"2026-05-13T09:44:42Z","snapshot_observed_at":"2026-08-09T11:33:28.649975Z","submitted_at":"2025-09-19T06:07:53Z","title":"UNIV: Unified Foundation Model for Infrared and Visible Modalities","version":3},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-05-18T16:28:48.494939Z"},"links":{"cited_paper":"/paper/2502.02257","citing_paper":"/paper/2509.15642"},"observation_digest":"sha256:d056c71d3cc0f0a7b972f262d4e051b6f4209a39ad562863a4860b26141e6652","observation_id":"deedfaa1-d2b8-4a73-a7ab-be4fab009306","resolution":{"observed_at":"2026-05-18T16:31:37.166147Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2502.02257/citation-record","integrity":"/paper/2502.02257/integrity","json":"/paper/2502.02257/citation-record.json","paper":"/paper/2502.02257"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T12:53:47.371706Z","title":"URL http://adas.cvc.uab.es/elektra/enigma-portfolio/cvc-14-visible-fir-day-night-pedestrian-sequen\\ -dataset/","venue":null,"work_id":"13d59e44-4603-4154-ae02-87c3f9b652c1","year":2016},"citing_paper":{"arxiv_id":"2502.02257","last_updated":"2025-03-20T13:55:08Z","snapshot_observed_at":"2026-08-10T12:43:23.653091Z","submitted_at":"2025-02-04T12:08:20Z","title":"UNIP: Rethinking Pre-trained Attention Patterns for Infrared Semantic Segmentation","version":2},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-09T12:53:45.541615Z"},"links":{"citing_paper":"/paper/2502.02257"},"observation_digest":"sha256:5730348fed261070a508e6243ba4d67d8494e177a821201fdfd058291e84e9a1","observation_id":"ecdfed03-3eed-41fc-93b6-fb2bbd2124a9","resolution":{"observed_at":"2026-08-09T12:53:47.377252Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T12:53:47.355686Z","title":"URL http://adas.cvc.uab.es/elektra/enigma-portfolio/item-1/","venue":null,"work_id":"c1403c85-b272-44aa-81ab-479954539040","year":2016},"citing_paper":{"arxiv_id":"2502.02257","last_updated":"2025-03-20T13:55:08Z","snapshot_observed_at":"2026-08-10T12:43:23.653091Z","submitted_at":"2025-02-04T12:08:20Z","title":"UNIP: Rethinking Pre-trained Attention Patterns for Infrared Semantic Segmentation","version":2},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-09T12:53:45.546961Z"},"links":{"citing_paper":"/paper/2502.02257"},"observation_digest":"sha256:97d8fade72eedc7435940ce88206bcc70aca9c3320ac894c39af3b001f84e145","observation_id":"f661000d-08b5-406c-87b8-2dc8de7392a2","resolution":{"observed_at":"2026-08-09T12:53:47.360848Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T12:53:47.338499Z","title":"Iris thermal/visible face database","venue":null,"work_id":"a62d26ab-53fa-4a71-98ba-229fce62de0e","year":null},"citing_paper":{"arxiv_id":"2502.02257","last_updated":"2025-03-20T13:55:08Z","snapshot_observed_at":"2026-08-10T12:43:23.653091Z","submitted_at":"2025-02-04T12:08:20Z","title":"UNIP: Rethinking Pre-trained Attention Patterns for Infrared Semantic Segmentation","version":2},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-09T12:53:45.552063Z"},"links":{"citing_paper":"/paper/2502.02257"},"observation_digest":"sha256:aee94fd662684c65bea8b792a965be63832a1466ec918755424e5870122a77ed","observation_id":"99ab05ae-3cf1-485e-a047-dab78a864d71","resolution":{"observed_at":"2026-08-09T12:53:47.343419Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T12:53:47.322667Z","title":"Bahnsen and Thomas B","venue":null,"work_id":"372a0338-de0b-4fd0-8014-65ba48517ce4","year":2019},"citing_paper":{"arxiv_id":"2502.02257","last_updated":"2025-03-20T13:55:08Z","snapshot_observed_at":"2026-08-10T12:43:23.653091Z","submitted_at":"2025-02-04T12:08:20Z","title":"UNIP: Rethinking Pre-trained Attention Patterns for Infrared Semantic Segmentation","version":2},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-09T12:53:45.557336Z"},"links":{"citing_paper":"/paper/2502.02257"},"observation_digest":"sha256:5f3f8cd1a4ab7418418cf0fbcfb1c3f29c89bc25f86d307ed15a276a880dbac3","observation_id":"5ab870f1-877c-49ca-85b3-6ff56d90588d","resolution":{"observed_at":"2026-08-09T12:53:47.327617Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T12:53:47.306599Z","title":"Yuille, Yuyin Zhou, and Cihang Xie","venue":null,"work_id":"e1610931-1ab9-4570-a7a4-c0dc9e42d7dc","year":2023},"citing_paper":{"arxiv_id":"2502.02257","last_updated":"2025-03-20T13:55:08Z","snapshot_observed_at":"2026-08-10T12:43:23.653091Z","submitted_at":"2025-02-04T12:08:20Z","title":"UNIP: Rethinking Pre-trained Attention Patterns for Infrared Semantic Segmentation","version":2},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-09T12:53:45.562186Z"},"links":{"citing_paper":"/paper/2502.02257"},"observation_digest":"sha256:35b9dd4672cfd344d42319ddc34bd0582ec4b8af8369f242c40c1fc28e5147dd","observation_id":"32a855c2-3213-4682-afe9-12ab0214159f","resolution":{"observed_at":"2026-08-09T12:53:47.312074Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T12:53:47.289821Z","title":"BeiT : BERT pre-training of image transformers","venue":null,"work_id":"cf0ed104-45fe-4877-9569-ddc7768e5992","year":2022},"citing_paper":{"arxiv_id":"2502.02257","last_updated":"2025-03-20T13:55:08Z","snapshot_observed_at":"2026-08-10T12:43:23.653091Z","submitted_at":"2025-02-04T12:08:20Z","title":"UNIP: Rethinking Pre-trained Attention Patterns for Infrared Semantic Segmentation","version":2},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-09T12:53:45.567178Z"},"links":{"citing_paper":"/paper/2502.02257"},"observation_digest":"sha256:9c32077ec67592a8307415c5bab02f39839edc6d2dfea827c6d896f1119f6f39","observation_id":"8e593292-2475-44d6-a490-5fba96b7b9e2","resolution":{"observed_at":"2026-08-09T12:53:47.295171Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T12:53:47.273300Z","title":"BIRDSAI : A dataset for detection and tracking in aerial thermal infrared videos","venue":null,"work_id":"c203e129-2411-4fb5-b0f5-512307bc698e","year":2020},"citing_paper":{"arxiv_id":"2502.02257","last_updated":"2025-03-20T13:55:08Z","snapshot_observed_at":"2026-08-10T12:43:23.653091Z","submitted_at":"2025-02-04T12:08:20Z","title":"UNIP: Rethinking Pre-trained Attention Patterns for Infrared Semantic Segmentation","version":2},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-09T12:53:45.571997Z"},"links":{"citing_paper":"/paper/2502.02257"},"observation_digest":"sha256:34da2d79c46ee21b27c6426c095d2ce0807833400150773ba6ad6273b6b3376f","observation_id":"4b2beb5b-87fa-4c16-b943-cf568e0eba22","resolution":{"observed_at":"2026-08-09T12:53:47.278465Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T12:53:45.577440Z","title":"End-to-end object detection with transformers","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2502.02257","last_updated":"2025-03-20T13:55:08Z","snapshot_observed_at":"2026-08-10T12:43:23.653091Z","submitted_at":"2025-02-04T12:08:20Z","title":"UNIP: Rethinking Pre-trained Attention Patterns for Infrared Semantic Segmentation","version":2},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-09T12:53:45.577440Z"},"links":{"citing_paper":"/paper/2502.02257"},"observation_digest":"sha256:6848618668820e51b5a3ef14bb8d453a27815c69756bcd9ef3d36ab7a9bbc45b","observation_id":"e75fe407-9d07-4bcd-bccb-74634afa588f","resolution":{"observed_at":"2026-08-09T12:53:45.577440Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T12:53:45.582079Z","title":"Emerging properties in self-supervised vision transformers","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2502.02257","last_updated":"2025-03-20T13:55:08Z","snapshot_observed_at":"2026-08-10T12:43:23.653091Z","submitted_at":"2025-02-04T12:08:20Z","title":"UNIP: Rethinking Pre-trained Attention Patterns for Infrared Semantic Segmentation","version":2},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-09T12:53:45.582079Z"},"links":{"citing_paper":"/paper/2502.02257"},"observation_digest":"sha256:13036adc69b197250940872ed518546d1c77bb6cec4708bf7473f4d2fe9f315b","observation_id":"767aa3da-77b0-49c8-a00a-6d2b46303dad","resolution":{"observed_at":"2026-08-09T12:53:45.582079Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T12:53:47.236948Z","title":"Atmospheric transmission and thermal inertia induced blind road segmentation with a large-scale dataset tbrsd","venue":null,"work_id":"d50500c8-aea7-4401-811b-1b92e90d99ef","year":2023},"citing_paper":{"arxiv_id":"2502.02257","last_updated":"2025-03-20T13:55:08Z","snapshot_observed_at":"2026-08-10T12:43:23.653091Z","submitted_at":"2025-02-04T12:08:20Z","title":"UNIP: Rethinking Pre-trained Attention Patterns for Infrared Semantic Segmentation","version":2},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-09T12:53:45.586818Z"},"links":{"citing_paper":"/paper/2502.02257"},"observation_digest":"sha256:f6af1ba2399ed9aa69bc6b0b2c088a207ccd0499bbb1408faccdc3c095841af2","observation_id":"d3c79189-4940-48f1-be90-9bc9edf1020e","resolution":{"observed_at":"2026-08-09T12:53:47.242242Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T12:53:47.220254Z","title":"Infrared city database, 2021 a","venue":null,"work_id":"b9415ac1-2105-487e-ab2c-9b1c942fd121","year":2021},"citing_paper":{"arxiv_id":"2502.02257","last_updated":"2025-03-20T13:55:08Z","snapshot_observed_at":"2026-08-10T12:43:23.653091Z","submitted_at":"2025-02-04T12:08:20Z","title":"UNIP: Rethinking Pre-trained Attention Patterns for Infrared Semantic Segmentation","version":2},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-09T12:53:45.591555Z"},"links":{"citing_paper":"/paper/2502.02257"},"observation_digest":"sha256:230df906e52833daf08b9b0a477baa20d35c0218911ba183510616c125425cd4","observation_id":"875dc59f-dbca-4569-aaa5-8ebd5dcb29c9","resolution":{"observed_at":"2026-08-09T12:53:47.226010Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T12:53:45.596521Z","title":"Encoder-decoder with atrous separable convolution for semantic image segmentation","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2502.02257","last_updated":"2025-03-20T13:55:08Z","snapshot_observed_at":"2026-08-10T12:43:23.653091Z","submitted_at":"2025-02-04T12:08:20Z","title":"UNIP: Rethinking Pre-trained Attention Patterns for Infrared Semantic Segmentation","version":2},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-09T12:53:45.596521Z"},"links":{"citing_paper":"/paper/2502.02257"},"observation_digest":"sha256:18aa5d6c11a2ae527deff296f43ac55720eacfc2f62987ae3abd49bb09cc775d","observation_id":"1b8c89c4-3248-4230-b607-d1f9b130b217","resolution":{"observed_at":"2026-08-09T12:53:45.596521Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T12:53:47.193655Z","title":"An empirical study of training self-supervised vision transformers","venue":null,"work_id":"a2770dc8-3181-42a8-a78f-c24dff5f2821","year":2021},"citing_paper":{"arxiv_id":"2502.02257","last_updated":"2025-03-20T13:55:08Z","snapshot_observed_at":"2026-08-10T12:43:23.653091Z","submitted_at":"2025-02-04T12:08:20Z","title":"UNIP: Rethinking Pre-trained Attention Patterns for Infrared Semantic Segmentation","version":2},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-09T12:53:45.601504Z"},"links":{"citing_paper":"/paper/2502.02257"},"observation_digest":"sha256:b37f2661e11604653dec5ec0357f944a456a4c8d60ba4dd9059ab011d429dd5d","observation_id":"de35f0ef-166c-4db2-9611-5323efde0063","resolution":{"observed_at":"2026-08-09T12:53:47.198865Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T12:53:45.606212Z","title":"Vision transformer adapter for dense predictions","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.02257","last_updated":"2025-03-20T13:55:08Z","snapshot_observed_at":"2026-08-10T12:43:23.653091Z","submitted_at":"2025-02-04T12:08:20Z","title":"UNIP: Rethinking Pre-trained Attention Patterns for Infrared Semantic Segmentation","version":2},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-09T12:53:45.606212Z"},"links":{"citing_paper":"/paper/2502.02257"},"observation_digest":"sha256:ffdf9beb596c16637ec331eff2645c68e47665a5bbc7d557fdb5ded1b2d826c4","observation_id":"3a17b849-1223-4d60-a729-cffd2155c35c","resolution":{"observed_at":"2026-08-09T12:53:45.606212Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T12:53:45.610674Z","title":"Schwing, Alexander Kirillov, and Rohit Girdhar","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2502.02257","last_updated":"2025-03-20T13:55:08Z","snapshot_observed_at":"2026-08-10T12:43:23.653091Z","submitted_at":"2025-02-04T12:08:20Z","title":"UNIP: Rethinking Pre-trained Attention Patterns for Infrared Semantic Segmentation","version":2},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-09T12:53:45.610674Z"},"links":{"citing_paper":"/paper/2502.02257"},"observation_digest":"sha256:bf44e55fab5771289de0ae08d9ef61ef606b6e95ca6b38446632f92d51884777","observation_id":"e20fe6da-33e0-4295-a876-a71c20c5b731","resolution":{"observed_at":"2026-08-09T12:53:45.610674Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T12:53:47.159184Z","title":"MMSegmentation : Openmmlab semantic segmentation toolbox and benchmark, 2020","venue":null,"work_id":"f62e999c-f31a-477e-91ff-3a6afdcd0690","year":2020},"citing_paper":{"arxiv_id":"2502.02257","last_updated":"2025-03-20T13:55:08Z","snapshot_observed_at":"2026-08-10T12:43:23.653091Z","submitted_at":"2025-02-04T12:08:20Z","title":"UNIP: Rethinking Pre-trained Attention Patterns for Infrared Semantic Segmentation","version":2},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-09T12:53:45.615158Z"},"links":{"citing_paper":"/paper/2502.02257"},"observation_digest":"sha256:dac064ea15f160ba4bf8101a448a0db657ff1d27da4d508ec5665dc7649e8544","observation_id":"e2aecf06-a01f-421f-bde8-4d26a9e0d4f2","resolution":{"observed_at":"2026-08-09T12:53:47.164092Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T12:53:45.619847Z","title":"ImageNet : A large-scale hierarchical image database","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2502.02257","last_updated":"2025-03-20T13:55:08Z","snapshot_observed_at":"2026-08-10T12:43:23.653091Z","submitted_at":"2025-02-04T12:08:20Z","title":"UNIP: Rethinking Pre-trained Attention Patterns for Infrared Semantic Segmentation","version":2},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-09T12:53:45.619847Z"},"links":{"citing_paper":"/paper/2502.02257"},"observation_digest":"sha256:9ec3397d720876547dd7dcc6fa6dfcfd0297e7d6e4024a7b298783b94b7848b7","observation_id":"3f57a3f1-7b94-4e6e-8c94-d964b8109b52","resolution":{"observed_at":"2026-08-09T12:53:45.619847Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T12:53:45.624570Z","title":"An image is worth 16x16 words: Transformers for image recognition at scale","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2502.02257","last_updated":"2025-03-20T13:55:08Z","snapshot_observed_at":"2026-08-10T12:43:23.653091Z","submitted_at":"2025-02-04T12:08:20Z","title":"UNIP: Rethinking Pre-trained Attention Patterns for Infrared Semantic Segmentation","version":2},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-09T12:53:45.624570Z"},"links":{"citing_paper":"/paper/2502.02257"},"observation_digest":"sha256:46426a88b6f3430d9747e19b74aceb4f41e36dd3e0b9177e12f998a9dae447ae","observation_id":"3ecfe921-c9cb-4b61-8dd9-f105fb9fb15f","resolution":{"observed_at":"2026-08-09T12:53:45.624570Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T12:53:47.121662Z","title":"EVA : Exploring the limits of masked visual representation learning at scale","venue":null,"work_id":"cda822e1-4006-47cb-8efa-8c69b5a871f7","year":2023},"citing_paper":{"arxiv_id":"2502.02257","last_updated":"2025-03-20T13:55:08Z","snapshot_observed_at":"2026-08-10T12:43:23.653091Z","submitted_at":"2025-02-04T12:08:20Z","title":"UNIP: Rethinking Pre-trained Attention Patterns for Infrared Semantic Segmentation","version":2},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-09T12:53:45.629060Z"},"links":{"citing_paper":"/paper/2502.02257"},"observation_digest":"sha256:f8f1af9e122c5cff6456ac1bbc7510b67a9265f406c64894d69be5397e059408","observation_id":"c12ada7f-9741-42f0-bd59-334a6599126d","resolution":{"observed_at":"2026-08-09T12:53:47.127609Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2401.14391","last_updated":"2025-04-10T07:50:15Z","snapshot_observed_at":"2026-08-10T12:42:54.894951Z","submitted_at":"2024-01-25T18:49:57Z","title":"Rethinking Patch Dependence for Masked Autoencoders","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.14391","snapshot_observed_at":"2026-08-09T12:53:45.633721Z","title":"Rethinking patch dependence for masked autoencoders","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.02257","last_updated":"2025-03-20T13:55:08Z","snapshot_observed_at":"2026-08-10T12:43:23.653091Z","submitted_at":"2025-02-04T12:08:20Z","title":"UNIP: Rethinking Pre-trained Attention Patterns for Infrared Semantic Segmentation","version":2},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-09T12:53:45.633721Z"},"links":{"cited_paper":"/paper/2401.14391","citing_paper":"/paper/2502.02257"},"observation_digest":"sha256:72516292969501fe042aa20b3fdde6df30657429afd029e98c340c2709e56e5d","observation_id":"bdbf581d-597c-452a-b522-e5701929ffab","resolution":{"observed_at":"2026-08-09T12:53:45.633721Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T12:53:47.106200Z","title":"MFNet : Towards real-time semantic segmentation for autonomous vehicles with multi-spectral scenes","venue":null,"work_id":"71b936f0-80b1-46ac-b229-e4aa3132485c","year":2017},"citing_paper":{"arxiv_id":"2502.02257","last_updated":"2025-03-20T13:55:08Z","snapshot_observed_at":"2026-08-10T12:43:23.653091Z","submitted_at":"2025-02-04T12:08:20Z","title":"UNIP: Rethinking Pre-trained Attention Patterns for Infrared Semantic Segmentation","version":2},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-09T12:53:45.638851Z"},"links":{"citing_paper":"/paper/2502.02257"},"observation_digest":"sha256:e0406d4daaf0b7dc67dec46c9186fb7135925f0891a800467a043032ac83429a","observation_id":"9b0ff69b-d1c5-4bd8-8a6f-ff0686c5f593","resolution":{"observed_at":"2026-08-09T12:53:47.111111Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T12:53:45.643430Z","title":"Deep residual learning for image recognition","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2502.02257","last_updated":"2025-03-20T13:55:08Z","snapshot_observed_at":"2026-08-10T12:43:23.653091Z","submitted_at":"2025-02-04T12:08:20Z","title":"UNIP: Rethinking Pre-trained Attention Patterns for Infrared Semantic Segmentation","version":2},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-08-09T12:53:45.643430Z"},"links":{"citing_paper":"/paper/2502.02257"},"observation_digest":"sha256:7ba8eabacb33a9bd6f944186c58b323e805693851366b40a10332eb739369f54","observation_id":"d92efad2-dd4e-4a5d-8c52-a0e29d1b083c","resolution":{"observed_at":"2026-08-09T12:53:45.643430Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T12:53:45.648223Z","title":"Masked autoencoders are scalable vision learners","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2502.02257","last_updated":"2025-03-20T13:55:08Z","snapshot_observed_at":"2026-08-10T12:43:23.653091Z","submitted_at":"2025-02-04T12:08:20Z","title":"UNIP: Rethinking Pre-trained Attention Patterns for Infrared Semantic Segmentation","version":2},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-08-09T12:53:45.648223Z"},"links":{"citing_paper":"/paper/2502.02257"},"observation_digest":"sha256:16ff25f2955a5580ed21033ca22cf69dc9abc620c42b8fc0285da01066a668dc","observation_id":"badebbd1-bb20-4cde-aa9a-c43646357f55","resolution":{"observed_at":"2026-08-09T12:53:45.648223Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1503.02531","last_updated":"2015-03-09T15:44:49Z","snapshot_observed_at":"2026-07-06T04:11:24.157003Z","submitted_at":"2015-03-09T15:44:49Z","title":"Distilling the Knowledge in a Neural Network","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1503.02531","snapshot_observed_at":"2026-08-09T12:53:45.652739Z","title":"Distilling the knowledge in a neural network","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2502.02257","last_updated":"2025-03-20T13:55:08Z","snapshot_observed_at":"2026-08-10T12:43:23.653091Z","submitted_at":"2025-02-04T12:08:20Z","title":"UNIP: Rethinking Pre-trained Attention Patterns for Infrared Semantic Segmentation","version":2},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-09T12:53:45.652739Z"},"links":{"cited_paper":"/paper/1503.02531","citing_paper":"/paper/2502.02257"},"observation_digest":"sha256:d3bbc196914b5bf13fac2e3bf6f37ef87038bc6146a0a4afacbe2cfbf69ce86d","observation_id":"75981902-5ef5-4217-aab1-685adc883c40","resolution":{"observed_at":"2026-08-09T12:53:45.652739Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2208.06049","last_updated":"2022-12-19T19:21:47Z","snapshot_observed_at":"2026-08-04T03:24:23.267133Z","submitted_at":"2022-08-11T21:58:36Z","title":"MILAN: Masked Image Pretraining on Language Assisted Representation","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2208.06049","snapshot_observed_at":"2026-08-09T12:53:45.657509Z","title":"Milan: Masked image pretraining on language assisted representation","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2502.02257","last_updated":"2025-03-20T13:55:08Z","snapshot_observed_at":"2026-08-10T12:43:23.653091Z","submitted_at":"2025-02-04T12:08:20Z","title":"UNIP: Rethinking Pre-trained Attention Patterns for Infrared Semantic Segmentation","version":2},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-08-09T12:53:45.657509Z"},"links":{"cited_paper":"/paper/2208.06049","citing_paper":"/paper/2502.02257"},"observation_digest":"sha256:9e07fedfe6635b1657e629a61bbb2f2e2667d2a98c9e06971a68ae91104441ba","observation_id":"50b8b9ef-af47-49b8-bf0c-c684e5cb8907","resolution":{"observed_at":"2026-08-09T12:53:45.657509Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T12:53:47.071477Z","title":"Multispectral pedestrian detection: Benchmark dataset and baselines","venue":null,"work_id":"adc8cde8-4a4a-406e-9e18-42f737d25e4a","year":2015},"citing_paper":{"arxiv_id":"2502.02257","last_updated":"2025-03-20T13:55:08Z","snapshot_observed_at":"2026-08-10T12:43:23.653091Z","submitted_at":"2025-02-04T12:08:20Z","title":"UNIP: Rethinking Pre-trained Attention Patterns for Infrared Semantic Segmentation","version":2},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-08-09T12:53:45.662400Z"},"links":{"citing_paper":"/paper/2502.02257"},"observation_digest":"sha256:c05970396d23ae84abf7aa4d7df1e8357a96a4a165d2db98000a2857cf2e6550","observation_id":"be2c3218-204e-49a9-a4eb-0badbf6522d7","resolution":{"observed_at":"2026-08-09T12:53:47.076418Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T12:53:47.056163Z","title":"LLVIP : A visible-infrared paired dataset for low-light vision","venue":null,"work_id":"cd4cd8d5-47ce-4944-9e74-cac272cfb56e","year":2021},"citing_paper":{"arxiv_id":"2502.02257","last_updated":"2025-03-20T13:55:08Z","snapshot_observed_at":"2026-08-10T12:43:23.653091Z","submitted_at":"2025-02-04T12:08:20Z","title":"UNIP: Rethinking Pre-trained Attention Patterns for Infrared Semantic Segmentation","version":2},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-08-09T12:53:45.666843Z"},"links":{"citing_paper":"/paper/2502.02257"},"observation_digest":"sha256:c440d6597747a484e0bc7ec5da0279a98c71cd44a178e75e47f7247905ad4f96","observation_id":"eca246d3-694e-4732-85dd-fb629d3c154c","resolution":{"observed_at":"2026-08-09T12:53:47.061106Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T12:53:47.040131Z","title":"Billion-scale similarity search with gpus","venue":null,"work_id":"f9f472c0-d3e1-4a0d-a521-dedd8bde01fb","year":2021},"citing_paper":{"arxiv_id":"2502.02257","last_updated":"2025-03-20T13:55:08Z","snapshot_observed_at":"2026-08-10T12:43:23.653091Z","submitted_at":"2025-02-04T12:08:20Z","title":"UNIP: Rethinking Pre-trained Attention Patterns for Infrared Semantic Segmentation","version":2},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-08-09T12:53:45.671724Z"},"links":{"citing_paper":"/paper/2502.02257"},"observation_digest":"sha256:ab36ecb08995cd569290589446c64665aef71b1ff401b3e0fefc9b1088f16dc5","observation_id":"a101ffe7-432f-49ad-87be-df87569d0d59","resolution":{"observed_at":"2026-08-09T12:53:47.045136Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T12:53:45.676233Z","title":"Similarity of neural network representations revisited","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2502.02257","last_updated":"2025-03-20T13:55:08Z","snapshot_observed_at":"2026-08-10T12:43:23.653091Z","submitted_at":"2025-02-04T12:08:20Z","title":"UNIP: Rethinking Pre-trained Attention Patterns for Infrared Semantic Segmentation","version":2},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-08-09T12:53:45.676233Z"},"links":{"citing_paper":"/paper/2502.02257"},"observation_digest":"sha256:35f831237298a0aebda642f5554e47873dd3be626d4a2b3e98d7f14f9aa1b770","observation_id":"b8ae9f8a-63fb-4911-bd4f-afcada548726","resolution":{"observed_at":"2026-08-09T12:53:45.676233Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T12:53:47.013020Z","title":"RGB-T object tracking: Benchmark and baseline","venue":null,"work_id":"9a1ff11e-491f-4a73-b7e9-1288b453c41b","year":2019},"citing_paper":{"arxiv_id":"2502.02257","last_updated":"2025-03-20T13:55:08Z","snapshot_observed_at":"2026-08-10T12:43:23.653091Z","submitted_at":"2025-02-04T12:08:20Z","title":"UNIP: Rethinking Pre-trained Attention Patterns for Infrared Semantic Segmentation","version":2},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-08-09T12:53:45.680460Z"},"links":{"citing_paper":"/paper/2502.02257"},"observation_digest":"sha256:6e01ba740fb40c6317276dde140493704360602d134b216fe499e852e2529d07","observation_id":"7908c5ec-55af-417d-ab1b-611f96547a05","resolution":{"observed_at":"2026-08-09T12:53:47.018546Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T12:53:46.995138Z","title":"Segmenting objects in day and night: Edge-conditioned cnn for thermal image semantic segmentation","venue":null,"work_id":"0f2074e1-a76d-46b0-b3ad-81ec51949b1c","year":2021},"citing_paper":{"arxiv_id":"2502.02257","last_updated":"2025-03-20T13:55:08Z","snapshot_observed_at":"2026-08-10T12:43:23.653091Z","submitted_at":"2025-02-04T12:08:20Z","title":"UNIP: Rethinking Pre-trained Attention Patterns for Infrared Semantic Segmentation","version":2},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-08-09T12:53:45.684513Z"},"links":{"citing_paper":"/paper/2502.02257"},"observation_digest":"sha256:353d83fcbf8b965ebf1047ebc607e6f55911c814060ec299cd26d6140c2bee04","observation_id":"956581c6-7e6e-4530-89ed-821aa1e07754","resolution":{"observed_at":"2026-08-09T12:53:47.000697Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T12:53:46.977732Z","title":"LasHeR : A large-scale high-diversity benchmark for rgbt tracking","venue":null,"work_id":"cc9d319d-92b4-4e0c-b52c-47bf34987451","year":2022},"citing_paper":{"arxiv_id":"2502.02257","last_updated":"2025-03-20T13:55:08Z","snapshot_observed_at":"2026-08-10T12:43:23.653091Z","submitted_at":"2025-02-04T12:08:20Z","title":"UNIP: Rethinking Pre-trained Attention Patterns for Infrared Semantic Segmentation","version":2},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-08-09T12:53:45.688538Z"},"links":{"citing_paper":"/paper/2502.02257"},"observation_digest":"sha256:16ee92ff37778d5c3dfb136f8175b91cf34b16d61c9f34fa17c0961cc99895a0","observation_id":"efa97621-003f-49c7-8ed4-c1b282264929","resolution":{"observed_at":"2026-08-09T12:53:46.983616Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T12:53:46.961724Z","title":"Infrared ship database, 2021","venue":null,"work_id":"7fec7d73-f811-49fb-822e-b4a09684baad","year":2021},"citing_paper":{"arxiv_id":"2502.02257","last_updated":"2025-03-20T13:55:08Z","snapshot_observed_at":"2026-08-10T12:43:23.653091Z","submitted_at":"2025-02-04T12:08:20Z","title":"UNIP: Rethinking Pre-trained Attention Patterns for Infrared Semantic Segmentation","version":2},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-08-09T12:53:45.692801Z"},"links":{"citing_paper":"/paper/2502.02257"},"observation_digest":"sha256:30da166d1306d2986109318605658f0cc2cd5de877a479b9dc95de018c4e923b","observation_id":"4a9e6ea2-837d-4a81-ab64-83d47ea2b544","resolution":{"observed_at":"2026-08-09T12:53:46.966870Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T12:53:46.946605Z","title":"Ni, and Heung-Yeung Shum","venue":null,"work_id":"b6279cf9-bc69-4026-88b5-e60c004b47ed","year":2023},"citing_paper":{"arxiv_id":"2502.02257","last_updated":"2025-03-20T13:55:08Z","snapshot_observed_at":"2026-08-10T12:43:23.653091Z","submitted_at":"2025-02-04T12:08:20Z","title":"UNIP: Rethinking Pre-trained Attention Patterns for Infrared Semantic Segmentation","version":2},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-08-09T12:53:45.696916Z"},"links":{"citing_paper":"/paper/2502.02257"},"observation_digest":"sha256:829c3a27f4ab0ad0adcb229deb7776523a4056a820aa4373c626b53f1371d8ac","observation_id":"6b3d17bf-5587-4cf8-bc3b-56c3844798fc","resolution":{"observed_at":"2026-08-09T12:53:46.951467Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T12:53:46.931183Z","title":"On-vehicle visible and infrared object detection database, 2021 b","venue":null,"work_id":"230f854c-70fa-4cc0-85d8-50885368c0e3","year":2021},"citing_paper":{"arxiv_id":"2502.02257","last_updated":"2025-03-20T13:55:08Z","snapshot_observed_at":"2026-08-10T12:43:23.653091Z","submitted_at":"2025-02-04T12:08:20Z","title":"UNIP: Rethinking Pre-trained Attention Patterns for Infrared Semantic Segmentation","version":2},"reference_index":35,"source":"arxiv_source","source_observed_at":"2026-08-09T12:53:45.701071Z"},"links":{"citing_paper":"/paper/2502.02257"},"observation_digest":"sha256:a8299272e27e3314a06412d9562bf4a4682b49f54d15d01d89b98322371cc61b","observation_id":"11ec7e85-7419-43ac-afd6-97b4f6a6b801","resolution":{"observed_at":"2026-08-09T12:53:46.936207Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T12:53:45.705450Z","title":"Exploring plain vision transformer backbones for object detection","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2502.02257","last_updated":"2025-03-20T13:55:08Z","snapshot_observed_at":"2026-08-10T12:43:23.653091Z","submitted_at":"2025-02-04T12:08:20Z","title":"UNIP: Rethinking Pre-trained Attention Patterns for Infrared Semantic Segmentation","version":2},"reference_index":36,"source":"arxiv_source","source_observed_at":"2026-08-09T12:53:45.705450Z"},"links":{"citing_paper":"/paper/2502.02257"},"observation_digest":"sha256:54611aebbd71c92c531760784c104fab37b3f476e08f1f1d9e99dac0eee81a8e","observation_id":"b0ed7cb6-a827-41a1-b44a-44313bf472b4","resolution":{"observed_at":"2026-08-09T12:53:45.705450Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T12:53:46.904533Z","title":"Lawrence Zitnick","venue":null,"work_id":"a6214292-7759-47fc-a93c-a36880010c8f","year":2014},"citing_paper":{"arxiv_id":"2502.02257","last_updated":"2025-03-20T13:55:08Z","snapshot_observed_at":"2026-08-10T12:43:23.653091Z","submitted_at":"2025-02-04T12:08:20Z","title":"UNIP: Rethinking Pre-trained Attention Patterns for Infrared Semantic Segmentation","version":2},"reference_index":37,"source":"arxiv_source","source_observed_at":"2026-08-09T12:53:45.709662Z"},"links":{"citing_paper":"/paper/2502.02257"},"observation_digest":"sha256:387d4d6452f66a98718724c905b98c7a99b0b12c2d96fb8bd404859307ae3aec","observation_id":"0ee4218e-7b8c-46f7-889e-7683ecfb2da1","resolution":{"observed_at":"2026-08-09T12:53:46.909309Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.00407","last_updated":"2024-09-14T14:58:26Z","snapshot_observed_at":"2026-08-04T09:42:12.140934Z","submitted_at":"2024-02-01T08:02:10Z","title":"InfMAE: A Foundation Model in the Infrared Modality","version":2},"cited_work":{"arxiv_id":"2402.00407","doi":null,"metadata_source":"pith","pith_arxiv_id":"2402.00407","snapshot_observed_at":"2026-08-09T12:53:46.334986Z","title":"InfMAE: A Foundation Model in the Infrared Modality","venue":"cs.CV","work_id":"07bd4c66-8106-49fa-8737-3cad32bb943b","year":2024},"citing_paper":{"arxiv_id":"2502.02257","last_updated":"2025-03-20T13:55:08Z","snapshot_observed_at":"2026-08-10T12:43:23.653091Z","submitted_at":"2025-02-04T12:08:20Z","title":"UNIP: Rethinking Pre-trained Attention Patterns for Infrared Semantic Segmentation","version":2},"reference_index":38,"source":"arxiv_source","source_observed_at":"2026-08-09T12:53:45.714072Z"},"links":{"cited_paper":"/paper/2402.00407","citing_paper":"/paper/2502.02257"},"observation_digest":"sha256:ac720b65983244830b18547ad8fd5d25ffea2696ca7a2ee2a385907de127d271","observation_id":"aa0203ca-e63f-4562-b401-0903c9056d29","resolution":{"observed_at":"2026-08-09T12:53:46.343262Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T12:53:46.888176Z","title":"Target-aware dual adversarial learning and a multi-scenario multi-modality benchmark to fuse infrared and visible for object detection","venue":null,"work_id":"731e2a08-a654-42ab-8f5e-daa6586a3b00","year":2022},"citing_paper":{"arxiv_id":"2502.02257","last_updated":"2025-03-20T13:55:08Z","snapshot_observed_at":"2026-08-10T12:43:23.653091Z","submitted_at":"2025-02-04T12:08:20Z","title":"UNIP: Rethinking Pre-trained Attention Patterns for Infrared Semantic Segmentation","version":2},"reference_index":39,"source":"arxiv_source","source_observed_at":"2026-08-09T12:53:45.718985Z"},"links":{"citing_paper":"/paper/2502.02257"},"observation_digest":"sha256:db6ed5497d29348952a60a8dc53ab43e6b647d90c117b4a046c134ce09db8787","observation_id":"02d6e45f-4ed0-4613-8555-28df9aaa49db","resolution":{"observed_at":"2026-08-09T12:53:46.893731Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T12:53:46.871586Z","title":"Cross-modal collaborative representation learning and a large-scale rgbt benchmark for crowd counting","venue":null,"work_id":"73bba6c6-695a-4b61-9966-5b7065ee361f","year":2021},"citing_paper":{"arxiv_id":"2502.02257","last_updated":"2025-03-20T13:55:08Z","snapshot_observed_at":"2026-08-10T12:43:23.653091Z","submitted_at":"2025-02-04T12:08:20Z","title":"UNIP: Rethinking Pre-trained Attention Patterns for Infrared Semantic Segmentation","version":2},"reference_index":40,"source":"arxiv_source","source_observed_at":"2026-08-09T12:53:45.723518Z"},"links":{"citing_paper":"/paper/2502.02257"},"observation_digest":"sha256:fe5560af3b948cb84418399158c43fc19345b8d1a7250353ffa6640b1b284605","observation_id":"233e0352-267d-44a2-8039-a6d83dce6beb","resolution":{"observed_at":"2026-08-09T12:53:46.876635Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T12:53:46.856316Z","title":"LSOTB-TIR : A large-scale high-diversity thermal infrared object tracking benchmark","venue":null,"work_id":"73263002-11c0-4b1b-bd70-ab503a766a14","year":2020},"citing_paper":{"arxiv_id":"2502.02257","last_updated":"2025-03-20T13:55:08Z","snapshot_observed_at":"2026-08-10T12:43:23.653091Z","submitted_at":"2025-02-04T12:08:20Z","title":"UNIP: Rethinking Pre-trained Attention Patterns for Infrared Semantic Segmentation","version":2},"reference_index":41,"source":"arxiv_source","source_observed_at":"2026-08-09T12:53:45.727974Z"},"links":{"citing_paper":"/paper/2502.02257"},"observation_digest":"sha256:d2749550e734039ec66e1d1533639a8ba9b95e21845f246576528440f15b445b","observation_id":"915019a6-bd30-459a-9c2d-d8dfaf2fe80c","resolution":{"observed_at":"2026-08-09T12:53:46.861396Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T12:53:46.840606Z","title":"General-purpose dual-sensor (infrared/visible) video database, 2021 b","venue":null,"work_id":"7a1b9855-6568-47a7-a224-74edbea7ea27","year":2021},"citing_paper":{"arxiv_id":"2502.02257","last_updated":"2025-03-20T13:55:08Z","snapshot_observed_at":"2026-08-10T12:43:23.653091Z","submitted_at":"2025-02-04T12:08:20Z","title":"UNIP: Rethinking Pre-trained Attention Patterns for Infrared Semantic Segmentation","version":2},"reference_index":42,"source":"arxiv_source","source_observed_at":"2026-08-09T12:53:45.732632Z"},"links":{"citing_paper":"/paper/2502.02257"},"observation_digest":"sha256:18c48f837723860bcb5916587be2d226ea66f993e3a66de7363f26ce888c3ee1","observation_id":"d7220bf5-d722-4837-bafd-08f36630310a","resolution":{"observed_at":"2026-08-09T12:53:46.845917Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T12:53:46.824902Z","title":"Infrared aerial photography database, 2021 c","venue":null,"work_id":"9ecc6a4a-f66d-4119-8545-f8ffe514e89e","year":2021},"citing_paper":{"arxiv_id":"2502.02257","last_updated":"2025-03-20T13:55:08Z","snapshot_observed_at":"2026-08-10T12:43:23.653091Z","submitted_at":"2025-02-04T12:08:20Z","title":"UNIP: Rethinking Pre-trained Attention Patterns for Infrared Semantic Segmentation","version":2},"reference_index":43,"source":"arxiv_source","source_observed_at":"2026-08-09T12:53:45.737252Z"},"links":{"citing_paper":"/paper/2502.02257"},"observation_digest":"sha256:3182dcf3849eedda7cb62e88ac61ff4d120d01d650ba592147f79b3e965dd64b","observation_id":"a4b77df4-da22-4ae2-bd49-0cde22fe29e8","resolution":{"observed_at":"2026-08-09T12:53:46.830172Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T12:53:46.809463Z","title":"Exploring target representations for masked autoencoders","venue":null,"work_id":"de6f48bb-611a-4551-88ea-0e3c9a3f6dc9","year":2024},"citing_paper":{"arxiv_id":"2502.02257","last_updated":"2025-03-20T13:55:08Z","snapshot_observed_at":"2026-08-10T12:43:23.653091Z","submitted_at":"2025-02-04T12:08:20Z","title":"UNIP: Rethinking Pre-trained Attention Patterns for Infrared Semantic Segmentation","version":2},"reference_index":44,"source":"arxiv_source","source_observed_at":"2026-08-09T12:53:45.742013Z"},"links":{"citing_paper":"/paper/2502.02257"},"observation_digest":"sha256:5f80c264d6d97896fe423ed4f5c10d7208b8a540c5e98363bdac66b6f7e1a170","observation_id":"756cf412-40fb-49aa-a78b-61395cf93f34","resolution":{"observed_at":"2026-08-09T12:53:46.814471Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T12:53:45.746591Z","title":"Fully convolutional networks for semantic segmentation","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2502.02257","last_updated":"2025-03-20T13:55:08Z","snapshot_observed_at":"2026-08-10T12:43:23.653091Z","submitted_at":"2025-02-04T12:08:20Z","title":"UNIP: Rethinking Pre-trained Attention Patterns for Infrared Semantic Segmentation","version":2},"reference_index":45,"source":"arxiv_source","source_observed_at":"2026-08-09T12:53:45.746591Z"},"links":{"citing_paper":"/paper/2502.02257"},"observation_digest":"sha256:f7157f1d1f1852609b16f274a7e0be10e6224ee90ca03e66a67372f9f005a463","observation_id":"61549e47-0e91-4515-9d46-47543d7ed4f8","resolution":{"observed_at":"2026-08-09T12:53:45.746591Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T12:53:46.783469Z","title":"Seasons in Drift : A long term thermal imaging dataset for studying concept drift","venue":null,"work_id":"bc9bd0d4-0336-41ea-bb5e-ff18425914c5","year":2021},"citing_paper":{"arxiv_id":"2502.02257","last_updated":"2025-03-20T13:55:08Z","snapshot_observed_at":"2026-08-10T12:43:23.653091Z","submitted_at":"2025-02-04T12:08:20Z","title":"UNIP: Rethinking Pre-trained Attention Patterns for Infrared Semantic Segmentation","version":2},"reference_index":46,"source":"arxiv_source","source_observed_at":"2026-08-09T12:53:45.751348Z"},"links":{"citing_paper":"/paper/2502.02257"},"observation_digest":"sha256:c6844c6a967899971a6e7b3fd4b5b0a1540e2a6d9a7d8322833e1b3ce03c41ec","observation_id":"ad0ec962-edbc-4a71-affc-d28d03f0eab5","resolution":{"observed_at":"2026-08-09T12:53:46.788737Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T12:53:45.756137Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.02257","last_updated":"2025-03-20T13:55:08Z","snapshot_observed_at":"2026-08-10T12:43:23.653091Z","submitted_at":"2025-02-04T12:08:20Z","title":"UNIP: Rethinking Pre-trained Attention Patterns for Infrared Semantic Segmentation","version":2},"reference_index":47,"source":"arxiv_source","source_observed_at":"2026-08-09T12:53:45.756137Z"},"links":{"citing_paper":"/paper/2502.02257"},"observation_digest":"sha256:4fa1af49635d3e6c16eb95a8100812dfd33ec264120429622c6ef56a62f723c2","observation_id":"db2d24db-01a3-4dae-a3c8-77a65b239e82","resolution":{"observed_at":"2026-08-09T12:53:45.756137Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T12:53:46.755446Z","title":"Multi-modal rgb--depth--thermal human body segmentation","venue":null,"work_id":"31c75a90-d8d6-406e-85d5-75de7a12f493","year":2016},"citing_paper":{"arxiv_id":"2502.02257","last_updated":"2025-03-20T13:55:08Z","snapshot_observed_at":"2026-08-10T12:43:23.653091Z","submitted_at":"2025-02-04T12:08:20Z","title":"UNIP: Rethinking Pre-trained Attention Patterns for Infrared Semantic Segmentation","version":2},"reference_index":48,"source":"arxiv_source","source_observed_at":"2026-08-09T12:53:45.760747Z"},"links":{"citing_paper":"/paper/2502.02257"},"observation_digest":"sha256:f2935b32539db431ebb36ecbe0fa3a01d733d6d960884e9e57bd0a83ac87fa40","observation_id":"6139eeff-4f7f-4cc4-8084-054aa6d6fa5f","resolution":{"observed_at":"2026-08-09T12:53:46.760486Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T12:53:46.739805Z","title":"What do self-supervised vision transformers learn? In ICLR, 2023","venue":null,"work_id":"5b84a02f-5a24-48b4-82ef-0b02e7ab0a22","year":2023},"citing_paper":{"arxiv_id":"2502.02257","last_updated":"2025-03-20T13:55:08Z","snapshot_observed_at":"2026-08-10T12:43:23.653091Z","submitted_at":"2025-02-04T12:08:20Z","title":"UNIP: Rethinking Pre-trained Attention Patterns for Infrared Semantic Segmentation","version":2},"reference_index":49,"source":"arxiv_source","source_observed_at":"2026-08-09T12:53:45.765280Z"},"links":{"citing_paper":"/paper/2502.02257"},"observation_digest":"sha256:ce3a8aea05d9f973e60670e1afdd3c832b24996261f8ed1b8745affcb51e3e90","observation_id":"10029816-063e-4d6e-9084-1bc2bca1b89e","resolution":{"observed_at":"2026-08-09T12:53:46.744995Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T12:53:46.724324Z","title":"PyTorch : An imperative style, high-performance deep learning library","venue":null,"work_id":"43e5a5da-b7cf-40b1-bdd7-c8f287a6f73b","year":2019},"citing_paper":{"arxiv_id":"2502.02257","last_updated":"2025-03-20T13:55:08Z","snapshot_observed_at":"2026-08-10T12:43:23.653091Z","submitted_at":"2025-02-04T12:08:20Z","title":"UNIP: Rethinking Pre-trained Attention Patterns for Infrared Semantic Segmentation","version":2},"reference_index":50,"source":"arxiv_source","source_observed_at":"2026-08-09T12:53:45.769862Z"},"links":{"citing_paper":"/paper/2502.02257"},"observation_digest":"sha256:cdd367f9bb8832fa7bc4c66f3e446e4b88535729055919b35440da0cdb0fa594","observation_id":"668050f6-88cf-4414-9e4b-32994eaa43f3","resolution":{"observed_at":"2026-08-09T12:53:46.729503Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T12:53:46.708374Z","title":"Mathematical contributions to the theory of evolution","venue":null,"work_id":"f27d2bd3-35f6-445f-8e2d-7e2aa57b5a6e","year":null},"citing_paper":{"arxiv_id":"2502.02257","last_updated":"2025-03-20T13:55:08Z","snapshot_observed_at":"2026-08-10T12:43:23.653091Z","submitted_at":"2025-02-04T12:08:20Z","title":"UNIP: Rethinking Pre-trained Attention Patterns for Infrared Semantic Segmentation","version":2},"reference_index":51,"source":"arxiv_source","source_observed_at":"2026-08-09T12:53:45.774510Z"},"links":{"citing_paper":"/paper/2502.02257"},"observation_digest":"sha256:527178dba56d0f623934f6a9f02775f872076c21c091c6815ac36acc62c840f4","observation_id":"6995c660-a5f9-433b-8014-b534f4a2cc39","resolution":{"observed_at":"2026-08-09T12:53:46.713406Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T12:53:46.692642Z","title":"TinyMIM : An empirical study of distilling mim pre-trained models","venue":null,"work_id":"8685069b-15f3-4486-aa27-4b5ced770279","year":2023},"citing_paper":{"arxiv_id":"2502.02257","last_updated":"2025-03-20T13:55:08Z","snapshot_observed_at":"2026-08-10T12:43:23.653091Z","submitted_at":"2025-02-04T12:08:20Z","title":"UNIP: Rethinking Pre-trained Attention Patterns for Infrared Semantic Segmentation","version":2},"reference_index":52,"source":"arxiv_source","source_observed_at":"2026-08-09T12:53:45.779568Z"},"links":{"citing_paper":"/paper/2502.02257"},"observation_digest":"sha256:12e971f605972717f75bf875ffef9c820800ec1cad49c93fbe12f1b5400ab58e","observation_id":"a5bfbf05-8460-4269-a74f-4f0ab58032f7","resolution":{"observed_at":"2026-08-09T12:53:46.697623Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T12:53:45.784065Z","title":"Indoor segmentation and support inference from rgbd images","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2502.02257","last_updated":"2025-03-20T13:55:08Z","snapshot_observed_at":"2026-08-10T12:43:23.653091Z","submitted_at":"2025-02-04T12:08:20Z","title":"UNIP: Rethinking Pre-trained Attention Patterns for Infrared Semantic Segmentation","version":2},"reference_index":53,"source":"arxiv_source","source_observed_at":"2026-08-09T12:53:45.784065Z"},"links":{"citing_paper":"/paper/2502.02257"},"observation_digest":"sha256:4bc4b4cea7dd9be1d11a75f06c33e3ac13853cf1a48cb1bac4f51f6aa3883c86","observation_id":"b8557b70-1bbe-418f-a7c4-79c7c4e04d46","resolution":{"observed_at":"2026-08-09T12:53:45.784065Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T12:53:46.666806Z","title":"Lichtenberg, and Jianxiong Xiao","venue":null,"work_id":"b82223f1-286c-4213-b264-e4b7a3c85772","year":2015},"citing_paper":{"arxiv_id":"2502.02257","last_updated":"2025-03-20T13:55:08Z","snapshot_observed_at":"2026-08-10T12:43:23.653091Z","submitted_at":"2025-02-04T12:08:20Z","title":"UNIP: Rethinking Pre-trained Attention Patterns for Infrared Semantic Segmentation","version":2},"reference_index":54,"source":"arxiv_source","source_observed_at":"2026-08-09T12:53:45.788703Z"},"links":{"citing_paper":"/paper/2502.02257"},"observation_digest":"sha256:5ca2729d00d25dec6be87d373370ab093ecaa5fbdd85287ecce210d9ef6260e4","observation_id":"5585b6d4-ffa2-4b9d-91ed-c0bfd6b32d69","resolution":{"observed_at":"2026-08-09T12:53:46.671574Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T12:53:46.651101Z","title":"Drone-based rgb-infrared cross-modality vehicle detection via uncertainty-aware learning","venue":null,"work_id":"0a2cc6ea-3eec-420b-9eff-990afa1f3195","year":2022},"citing_paper":{"arxiv_id":"2502.02257","last_updated":"2025-03-20T13:55:08Z","snapshot_observed_at":"2026-08-10T12:43:23.653091Z","submitted_at":"2025-02-04T12:08:20Z","title":"UNIP: Rethinking Pre-trained Attention Patterns for Infrared Semantic Segmentation","version":2},"reference_index":55,"source":"arxiv_source","source_observed_at":"2026-08-09T12:53:45.793153Z"},"links":{"citing_paper":"/paper/2502.02257"},"observation_digest":"sha256:20a7f30d6d3ee6aec6065cd0eecaf583db219397bf6b4de6ef0f69968062f9b3","observation_id":"b62560d3-77f0-4d2f-9e89-b495d7156ad0","resolution":{"observed_at":"2026-08-09T12:53:46.656359Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T12:53:46.635940Z","title":"Multispectral object detection for autonomous vehicles","venue":null,"work_id":"f36e0cd9-b1fe-44c6-976f-1a5b22a75149","year":2017},"citing_paper":{"arxiv_id":"2502.02257","last_updated":"2025-03-20T13:55:08Z","snapshot_observed_at":"2026-08-10T12:43:23.653091Z","submitted_at":"2025-02-04T12:08:20Z","title":"UNIP: Rethinking Pre-trained Attention Patterns for Infrared Semantic Segmentation","version":2},"reference_index":56,"source":"arxiv_source","source_observed_at":"2026-08-09T12:53:45.797622Z"},"links":{"citing_paper":"/paper/2502.02257"},"observation_digest":"sha256:09f70d3a22c9aa6f7f9e77f139a5b4de2996851f4f3059449b2cca895b9d38a7","observation_id":"dc57d9a0-fef2-4b26-8e1b-d29728e2490f","resolution":{"observed_at":"2026-08-09T12:53:46.640858Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T12:53:46.621245Z","title":"Training data-efficient image transformers & distillation through attention","venue":null,"work_id":"130707fa-05e4-4ef7-af81-94c78de96910","year":2021},"citing_paper":{"arxiv_id":"2502.02257","last_updated":"2025-03-20T13:55:08Z","snapshot_observed_at":"2026-08-10T12:43:23.653091Z","submitted_at":"2025-02-04T12:08:20Z","title":"UNIP: Rethinking Pre-trained Attention Patterns for Infrared Semantic Segmentation","version":2},"reference_index":57,"source":"arxiv_source","source_observed_at":"2026-08-09T12:53:45.802067Z"},"links":{"citing_paper":"/paper/2502.02257"},"observation_digest":"sha256:cc816f9a2ba6e488235bd6a56820cccd0ec908a7c1518f3d4034abd8cd9a52d7","observation_id":"cdf34d89-04f0-419b-a641-9621b90a5d1a","resolution":{"observed_at":"2026-08-09T12:53:46.625993Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T12:53:46.605910Z","title":"DeiT III : Revenge of the vit","venue":null,"work_id":"3a171c83-4a9a-4359-b999-dbd29d14a910","year":2022},"citing_paper":{"arxiv_id":"2502.02257","last_updated":"2025-03-20T13:55:08Z","snapshot_observed_at":"2026-08-10T12:43:23.653091Z","submitted_at":"2025-02-04T12:08:20Z","title":"UNIP: Rethinking Pre-trained Attention Patterns for Infrared Semantic Segmentation","version":2},"reference_index":58,"source":"arxiv_source","source_observed_at":"2026-08-09T12:53:45.806767Z"},"links":{"citing_paper":"/paper/2502.02257"},"observation_digest":"sha256:d58504e8e46e6018536f591b9a817523f7a6db680fccdd7b74e924757d3637a7","observation_id":"24dcf3c8-9232-42ed-975f-8f10c53f0e52","resolution":{"observed_at":"2026-08-09T12:53:46.610742Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T12:53:46.589390Z","title":"RGBT Salient Object Detection : A large-scale dataset and benchmark","venue":null,"work_id":"ec633c48-080f-414f-a3ba-c723625a864d","year":2023},"citing_paper":{"arxiv_id":"2502.02257","last_updated":"2025-03-20T13:55:08Z","snapshot_observed_at":"2026-08-10T12:43:23.653091Z","submitted_at":"2025-02-04T12:08:20Z","title":"UNIP: Rethinking Pre-trained Attention Patterns for Infrared Semantic Segmentation","version":2},"reference_index":59,"source":"arxiv_source","source_observed_at":"2026-08-09T12:53:45.811589Z"},"links":{"citing_paper":"/paper/2502.02257"},"observation_digest":"sha256:455b77038168bf47f3e99c114d46949bf57a07b00ef366e1a8615a3f5dd0f76b","observation_id":"fb3886ae-5a9e-4381-a228-be8d5c22a7a3","resolution":{"observed_at":"2026-08-09T12:53:46.594841Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T12:53:46.574021Z","title":"A closer look at self-supervised lightweight vision transformers","venue":null,"work_id":"37045958-0662-40e6-9f76-2b8556c08278","year":2023},"citing_paper":{"arxiv_id":"2502.02257","last_updated":"2025-03-20T13:55:08Z","snapshot_observed_at":"2026-08-10T12:43:23.653091Z","submitted_at":"2025-02-04T12:08:20Z","title":"UNIP: Rethinking Pre-trained Attention Patterns for Infrared Semantic Segmentation","version":2},"reference_index":60,"source":"arxiv_source","source_observed_at":"2026-08-09T12:53:45.817174Z"},"links":{"citing_paper":"/paper/2502.02257"},"observation_digest":"sha256:21a750cccdfce651b7e9b290acc21e4b68b0ffeab65cf25a29e347756c4e0f8b","observation_id":"4d10340c-c2fa-4b81-88fb-7270734eccf2","resolution":{"observed_at":"2026-08-09T12:53:46.579099Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T12:53:46.556659Z","title":"Unified perceptual parsing for scene understanding","venue":null,"work_id":"abc26a9e-781a-4449-85b7-7a90bc7bd2da","year":2018},"citing_paper":{"arxiv_id":"2502.02257","last_updated":"2025-03-20T13:55:08Z","snapshot_observed_at":"2026-08-10T12:43:23.653091Z","submitted_at":"2025-02-04T12:08:20Z","title":"UNIP: Rethinking Pre-trained Attention Patterns for Infrared Semantic Segmentation","version":2},"reference_index":61,"source":"arxiv_source","source_observed_at":"2026-08-09T12:53:45.821949Z"},"links":{"citing_paper":"/paper/2502.02257"},"observation_digest":"sha256:c0ab0cce6d995813bf8740463084c4ef097c253f3a1d3409187109db27276473","observation_id":"aa3a6241-430d-4488-a2b2-4a3df26092c4","resolution":{"observed_at":"2026-08-09T12:53:46.562273Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T12:53:46.540545Z","title":"Alvarez, and Ping Luo","venue":null,"work_id":"42942759-20c4-42cb-84c2-f64d65319f09","year":2021},"citing_paper":{"arxiv_id":"2502.02257","last_updated":"2025-03-20T13:55:08Z","snapshot_observed_at":"2026-08-10T12:43:23.653091Z","submitted_at":"2025-02-04T12:08:20Z","title":"UNIP: Rethinking Pre-trained Attention Patterns for Infrared Semantic Segmentation","version":2},"reference_index":62,"source":"arxiv_source","source_observed_at":"2026-08-09T12:53:45.826586Z"},"links":{"citing_paper":"/paper/2502.02257"},"observation_digest":"sha256:f11f795f6f86f45759120102d089fbbd294831165e8f694c700b10bc9e004a0e","observation_id":"4fe5c991-830b-4b76-8fec-23fb65f2bb6c","resolution":{"observed_at":"2026-08-09T12:53:46.545373Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T12:53:46.524900Z","title":"MCNet : Multi-level correction network for thermal image semantic segmentation of nighttime driving scene","venue":null,"work_id":"5ed62841-c4e3-4928-a5fa-5c64f8336d71","year":2021},"citing_paper":{"arxiv_id":"2502.02257","last_updated":"2025-03-20T13:55:08Z","snapshot_observed_at":"2026-08-10T12:43:23.653091Z","submitted_at":"2025-02-04T12:08:20Z","title":"UNIP: Rethinking Pre-trained Attention Patterns for Infrared Semantic Segmentation","version":2},"reference_index":63,"source":"arxiv_source","source_observed_at":"2026-08-09T12:53:45.831142Z"},"links":{"citing_paper":"/paper/2502.02257"},"observation_digest":"sha256:37fa8e4018b67f9f202ff967931b11d27d89a12c39615f35d85d73eb92c5645d","observation_id":"45ebcea5-3e28-4ab5-867a-09243e22b37f","resolution":{"observed_at":"2026-08-09T12:53:46.529980Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T12:53:46.509031Z","title":"EfficientSAM : Leveraged masked image pretraining for efficient segment anything","venue":null,"work_id":"af6e7e88-a311-40ed-9f2d-441562e635c8","year":2024},"citing_paper":{"arxiv_id":"2502.02257","last_updated":"2025-03-20T13:55:08Z","snapshot_observed_at":"2026-08-10T12:43:23.653091Z","submitted_at":"2025-02-04T12:08:20Z","title":"UNIP: Rethinking Pre-trained Attention Patterns for Infrared Semantic Segmentation","version":2},"reference_index":64,"source":"arxiv_source","source_observed_at":"2026-08-09T12:53:45.835601Z"},"links":{"citing_paper":"/paper/2502.02257"},"observation_digest":"sha256:ad086ea58f291ae132e463a83fde9c89aa3d7a0f8a4d26e78b3ba237ffb6dcd8","observation_id":"384da174-4137-4ee1-ad21-b38b3b16f49d","resolution":{"observed_at":"2026-08-09T12:53:46.513988Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T12:53:46.492061Z","title":"ROMA : Cross-domain region similarity matching for unpaired nighttime infrared to daytime visible video translation","venue":null,"work_id":"60a4fad1-da2e-4e1e-9c3e-17a8e18fd910","year":2022},"citing_paper":{"arxiv_id":"2502.02257","last_updated":"2025-03-20T13:55:08Z","snapshot_observed_at":"2026-08-10T12:43:23.653091Z","submitted_at":"2025-02-04T12:08:20Z","title":"UNIP: Rethinking Pre-trained Attention Patterns for Infrared Semantic Segmentation","version":2},"reference_index":65,"source":"arxiv_source","source_observed_at":"2026-08-09T12:53:45.840470Z"},"links":{"citing_paper":"/paper/2502.02257"},"observation_digest":"sha256:9c73c0371b537f35e18b49cc2bcaa4f3350bc2e84f9c95849f89bfd1fd53b2f8","observation_id":"18ec3f43-03d7-4af1-88f5-8cdff0974f56","resolution":{"observed_at":"2026-08-09T12:53:46.497385Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T12:53:46.476083Z","title":"Visible-Thermal UAV Tracking : A large-scale benchmark and new baseline","venue":null,"work_id":"76c5383a-4a61-4017-967d-c3a6177b62ef","year":2022},"citing_paper":{"arxiv_id":"2502.02257","last_updated":"2025-03-20T13:55:08Z","snapshot_observed_at":"2026-08-10T12:43:23.653091Z","submitted_at":"2025-02-04T12:08:20Z","title":"UNIP: Rethinking Pre-trained Attention Patterns for Infrared Semantic Segmentation","version":2},"reference_index":66,"source":"arxiv_source","source_observed_at":"2026-08-09T12:53:45.845080Z"},"links":{"citing_paper":"/paper/2502.02257"},"observation_digest":"sha256:545a386bdc2341be12ce83f5e1086e5296779271e2fd53570992f6d5f93750ec","observation_id":"360d50f3-6327-4913-a6af-309e279a7c35","resolution":{"observed_at":"2026-08-09T12:53:46.481219Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2312.08192","last_updated":"2023-12-13T14:57:28Z","snapshot_observed_at":"2026-08-07T02:53:27.220470Z","submitted_at":"2023-12-13T14:57:28Z","title":"PAD: Self-Supervised Pre-Training with Patchwise-Scale Adapter for Infrared Images","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.08192","snapshot_observed_at":"2026-08-09T12:53:45.849833Z","title":"PAD : Self-supervised pre-training with patchwise-scale adapter for infrared images","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.02257","last_updated":"2025-03-20T13:55:08Z","snapshot_observed_at":"2026-08-10T12:43:23.653091Z","submitted_at":"2025-02-04T12:08:20Z","title":"UNIP: Rethinking Pre-trained Attention Patterns for Infrared Semantic Segmentation","version":2},"reference_index":67,"source":"arxiv_source","source_observed_at":"2026-08-09T12:53:45.849833Z"},"links":{"cited_paper":"/paper/2312.08192","citing_paper":"/paper/2502.02257"},"observation_digest":"sha256:413f62aa49bd6cd873194792915dcc32a669d04097279ed50db514ab6e5bc40c","observation_id":"1973faa9-78e6-407e-8d78-26e34bf1277b","resolution":{"observed_at":"2026-08-09T12:53:45.849833Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T12:53:45.964216Z","title":"Pyramid scene parsing network","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2502.02257","last_updated":"2025-03-20T13:55:08Z","snapshot_observed_at":"2026-08-10T12:43:23.653091Z","submitted_at":"2025-02-04T12:08:20Z","title":"UNIP: Rethinking Pre-trained Attention Patterns for Infrared Semantic Segmentation","version":2},"reference_index":68,"source":"arxiv_source","source_observed_at":"2026-08-09T12:53:45.964216Z"},"links":{"citing_paper":"/paper/2502.02257"},"observation_digest":"sha256:c09e9beaf72241e92832d736a85d9d065d1ed506e7b6483a59f74a141a40d804","observation_id":"83b43470-89aa-424c-ad84-e236e4f08cd3","resolution":{"observed_at":"2026-08-09T12:53:45.964216Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T12:53:45.969335Z","title":"Scene parsing through ade20k dataset","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2502.02257","last_updated":"2025-03-20T13:55:08Z","snapshot_observed_at":"2026-08-10T12:43:23.653091Z","submitted_at":"2025-02-04T12:08:20Z","title":"UNIP: Rethinking Pre-trained Attention Patterns for Infrared Semantic Segmentation","version":2},"reference_index":69,"source":"arxiv_source","source_observed_at":"2026-08-09T12:53:45.969335Z"},"links":{"citing_paper":"/paper/2502.02257"},"observation_digest":"sha256:35426d759047093a3d1e07aa4154b2ce3ee4546a09f6ee6fc76da5f7b264a0bf","observation_id":"c916ab5f-7fcb-487d-85ce-1029413e4ba8","resolution":{"observed_at":"2026-08-09T12:53:45.969335Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T12:53:46.439790Z","title":"Image BERT pre-training with online tokenizer","venue":null,"work_id":"f62df2b2-2186-49dc-8229-02c0972440f0","year":2022},"citing_paper":{"arxiv_id":"2502.02257","last_updated":"2025-03-20T13:55:08Z","snapshot_observed_at":"2026-08-10T12:43:23.653091Z","submitted_at":"2025-02-04T12:08:20Z","title":"UNIP: Rethinking Pre-trained Attention Patterns for Infrared Semantic Segmentation","version":2},"reference_index":70,"source":"arxiv_source","source_observed_at":"2026-08-09T12:53:45.974006Z"},"links":{"citing_paper":"/paper/2502.02257"},"observation_digest":"sha256:f4049cc050b1aa013af883352bc35c49490ec125e28d1cea4efa4e3027453b42","observation_id":"e04844d9-d443-4890-a4da-8f33c53c49b0","resolution":{"observed_at":"2026-08-09T12:53:46.445323Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T12:53:45.978460Z","title":"write newline","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.02257","last_updated":"2025-03-20T13:55:08Z","snapshot_observed_at":"2026-08-10T12:43:23.653091Z","submitted_at":"2025-02-04T12:08:20Z","title":"UNIP: Rethinking Pre-trained Attention Patterns for Infrared Semantic Segmentation","version":2},"reference_index":71,"source":"arxiv_source","source_observed_at":"2026-08-09T12:53:45.978460Z"},"links":{"citing_paper":"/paper/2502.02257"},"observation_digest":"sha256:68fa978f9b90d778694ea0278a1422940d3ff432ae44b0afd596d55165620814","observation_id":"da568c67-33a8-4a31-8ca5-c3e4b8cfd93a","resolution":{"observed_at":"2026-08-09T12:53:45.978460Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T12:53:45.983743Z","title":"@esa (Ref","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.02257","last_updated":"2025-03-20T13:55:08Z","snapshot_observed_at":"2026-08-10T12:43:23.653091Z","submitted_at":"2025-02-04T12:08:20Z","title":"UNIP: Rethinking Pre-trained Attention Patterns for Infrared Semantic Segmentation","version":2},"reference_index":72,"source":"arxiv_source","source_observed_at":"2026-08-09T12:53:45.983743Z"},"links":{"citing_paper":"/paper/2502.02257"},"observation_digest":"sha256:d54258b2c9c1bb764ff4bc7389d7809a6023ed83b73a625d8c728bfa02b65224","observation_id":"7da20a57-80d2-4d86-be75-07a34ab68012","resolution":{"observed_at":"2026-08-09T12:53:45.983743Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T12:53:45.988839Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.02257","last_updated":"2025-03-20T13:55:08Z","snapshot_observed_at":"2026-08-10T12:43:23.653091Z","submitted_at":"2025-02-04T12:08:20Z","title":"UNIP: Rethinking Pre-trained Attention Patterns for Infrared Semantic Segmentation","version":2},"reference_index":73,"source":"arxiv_source","source_observed_at":"2026-08-09T12:53:45.988839Z"},"links":{"citing_paper":"/paper/2502.02257"},"observation_digest":"sha256:cd0075033d47ed7f8efa6f802c5717be5e06f4e4697e53fc43d62679140f3a11","observation_id":"a2877dbe-e442-48f4-b834-81ba023d7042","resolution":{"observed_at":"2026-08-09T12:53:45.988839Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T12:53:45.993773Z","title":"Therefore, we focus on enhancing small pre-trained models by introducing a comprehensive framework, UNIP, and validating its effectiveness through extensive experiments","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.02257","last_updated":"2025-03-20T13:55:08Z","snapshot_observed_at":"2026-08-10T12:43:23.653091Z","submitted_at":"2025-02-04T12:08:20Z","title":"UNIP: Rethinking Pre-trained Attention Patterns for Infrared Semantic Segmentation","version":2},"reference_index":74,"source":"arxiv_source","source_observed_at":"2026-08-09T12:53:45.993773Z"},"links":{"citing_paper":"/paper/2502.02257"},"observation_digest":"sha256:b72a0421fc1a01d4853090c93c22abb37abef748d4adb0fe45cdce8d82405e43","observation_id":"986f4085-e807-449d-89f8-17c94dba445d","resolution":{"observed_at":"2026-08-09T12:53:45.993773Z","resolver_source":null,"status":"malformed_identifier"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2502.02257","last_updated":"2025-03-20T13:55:08Z","latest_version":2,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-10T12:43:23.653091Z","submitted_at":"2025-02-04T12:08:20Z","title":"UNIP: Rethinking Pre-trained Attention Patterns for Infrared Semantic Segmentation"},"reference_resolution":{"displayed":74,"state_counts":{"malformed_identifier":1,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":23,"verified_exact":1,"verified_fuzzy":49},"total_outbound_references":74},"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 74 of 74 outbound references and 1 inbound Pith citation observation for arXiv:2502.02257."}