{"as_of":"2026-08-08T08:28:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:7472336ff9b726ac284a8ac24ae2a3f8d5c0b8d2750fb664ce36bdd734ab66d4","coverage":[{"denominator":84,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":84,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-03T09:48:56.732951Z","state":"measured"},{"denominator":84,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":84,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2601.12500/citation-record","integrity":"/paper/2601.12500/integrity","json":"/paper/2601.12500/citation-record.json","paper":"/paper/2601.12500"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T09:48:46.024981Z","title":"Integrated sensing and communication for low altitude econ- omy: Opportunities and challenges,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2601.12500","last_updated":"2026-05-28T09:52:35Z","snapshot_observed_at":"2026-08-07T11:18:00.769993Z","submitted_at":"2026-01-18T17:17:31Z","title":"Video Individual Counting and Tracking from Moving Drones: A Benchmark and Methods","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-03T09:48:46.024981Z"},"links":{"citing_paper":"/paper/2601.12500"},"observation_digest":"sha256:0a0aae56ffa84fefc5f982a3f3f913532160d7b947830f77cfd8e0d27d6644cb","observation_id":"5dde05ce-c267-4f65-a043-3fe3194eae97","resolution":{"observed_at":"2026-08-03T09:48:46.024981Z","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":"2026-08-03T09:48:46.115566Z","title":"Unmanned aerial vehicles based low-altitude economy with lifecycle techno-economic-environmental analysis for sustainable and smart cities,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2601.12500","last_updated":"2026-05-28T09:52:35Z","snapshot_observed_at":"2026-08-07T11:18:00.769993Z","submitted_at":"2026-01-18T17:17:31Z","title":"Video Individual Counting and Tracking from Moving Drones: A Benchmark and Methods","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-03T09:48:46.115566Z"},"links":{"citing_paper":"/paper/2601.12500"},"observation_digest":"sha256:3ce02b505ff282273e9c9aea28d8088e8d4f07f98ee54ece8bccf261389668b6","observation_id":"35c4c085-7e47-4f94-ab89-99a17e7136fc","resolution":{"observed_at":"2026-08-03T09:48:46.115566Z","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":"2026-08-03T09:48:46.294586Z","title":"Low-altitude intelligent transportation: System architecture, infrastructure, and key technologies,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2601.12500","last_updated":"2026-05-28T09:52:35Z","snapshot_observed_at":"2026-08-07T11:18:00.769993Z","submitted_at":"2026-01-18T17:17:31Z","title":"Video Individual Counting and Tracking from Moving Drones: A Benchmark and Methods","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-03T09:48:46.294586Z"},"links":{"citing_paper":"/paper/2601.12500"},"observation_digest":"sha256:eb0e4f3ea435783d31504a9d60db2eb69a66ac9ecdac2004bf20f79f37d87e2f","observation_id":"6d238a47-fd58-4cfd-b798-c51552507fe2","resolution":{"observed_at":"2026-08-03T09:48:46.294586Z","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":"2026-08-03T09:48:46.444480Z","title":"Learning to count objects in images,","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2601.12500","last_updated":"2026-05-28T09:52:35Z","snapshot_observed_at":"2026-08-07T11:18:00.769993Z","submitted_at":"2026-01-18T17:17:31Z","title":"Video Individual Counting and Tracking from Moving Drones: A Benchmark and Methods","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-03T09:48:46.444480Z"},"links":{"citing_paper":"/paper/2601.12500"},"observation_digest":"sha256:c7d208a260017c7e7038b88ab7f1ee1013a87f37fbaa04c74fd9169ccc03d491","observation_id":"2d497da1-6a6d-4f38-898f-2026bbc26d88","resolution":{"observed_at":"2026-08-03T09:48:46.444480Z","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":"2026-08-03T09:48:46.571169Z","title":"Csrnet: Dilated convolutional neural net- works for understanding the highly congested scenes,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2601.12500","last_updated":"2026-05-28T09:52:35Z","snapshot_observed_at":"2026-08-07T11:18:00.769993Z","submitted_at":"2026-01-18T17:17:31Z","title":"Video Individual Counting and Tracking from Moving Drones: A Benchmark and Methods","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-03T09:48:46.571169Z"},"links":{"citing_paper":"/paper/2601.12500"},"observation_digest":"sha256:995869bba2aea94e3283ea32c6e5d66bf93500f46b97ac7e31ea993066b8a2a4","observation_id":"7e0dc8a4-49e0-4ff3-a213-76842e50de1c","resolution":{"observed_at":"2026-08-03T09:48:46.571169Z","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":"2026-08-03T09:48:46.727881Z","title":"Regressor- segmenter mutual prompt learning for crowd counting,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2601.12500","last_updated":"2026-05-28T09:52:35Z","snapshot_observed_at":"2026-08-07T11:18:00.769993Z","submitted_at":"2026-01-18T17:17:31Z","title":"Video Individual Counting and Tracking from Moving Drones: A Benchmark and Methods","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-03T09:48:46.727881Z"},"links":{"citing_paper":"/paper/2601.12500"},"observation_digest":"sha256:792b04f1e3bc72657d9220af164d13f340e3a76c441b70ab9bf02a5637332bb4","observation_id":"c72745a4-5882-4421-9f30-52c92b0e37e8","resolution":{"observed_at":"2026-08-03T09:48:46.727881Z","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":"2026-08-03T09:48:46.826683Z","title":"Rethinking counting and localization in crowds: A purely point-based framework,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2601.12500","last_updated":"2026-05-28T09:52:35Z","snapshot_observed_at":"2026-08-07T11:18:00.769993Z","submitted_at":"2026-01-18T17:17:31Z","title":"Video Individual Counting and Tracking from Moving Drones: A Benchmark and Methods","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-03T09:48:46.826683Z"},"links":{"citing_paper":"/paper/2601.12500"},"observation_digest":"sha256:c8905ba622311e5d56d194003243cabd8adb4f814c026f0e170167457dc9ee8e","observation_id":"6fcbfff9-aa24-4ef6-9a7e-169cb211bb66","resolution":{"observed_at":"2026-08-03T09:48:46.826683Z","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":"2026-08-03T09:48:46.942176Z","title":"Learning from synthetic data for crowd counting in the wild,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2601.12500","last_updated":"2026-05-28T09:52:35Z","snapshot_observed_at":"2026-08-07T11:18:00.769993Z","submitted_at":"2026-01-18T17:17:31Z","title":"Video Individual Counting and Tracking from Moving Drones: A Benchmark and Methods","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-03T09:48:46.942176Z"},"links":{"citing_paper":"/paper/2601.12500"},"observation_digest":"sha256:c97e2c5e52d559b515552fe72faa12195991d28b83d519d89815d5f4edaefbd9","observation_id":"403dfa57-e494-422a-bba1-abb0c48be002","resolution":{"observed_at":"2026-08-03T09:48:46.942176Z","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":"2026-08-03T09:48:47.050993Z","title":"Multiple object tracking as id prediction,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2601.12500","last_updated":"2026-05-28T09:52:35Z","snapshot_observed_at":"2026-08-07T11:18:00.769993Z","submitted_at":"2026-01-18T17:17:31Z","title":"Video Individual Counting and Tracking from Moving Drones: A Benchmark and Methods","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-03T09:48:47.050993Z"},"links":{"citing_paper":"/paper/2601.12500"},"observation_digest":"sha256:24764d53ef754889f9f42958bd4d5f0a342b05912f06acd425ed372e536c3093","observation_id":"fe9b5ee7-c560-4f79-99bc-efaba5c26b4f","resolution":{"observed_at":"2026-08-03T09:48:47.050993Z","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":"2026-08-03T09:48:47.195038Z","title":"Drone-assisted public safety net- works: The security aspect,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2601.12500","last_updated":"2026-05-28T09:52:35Z","snapshot_observed_at":"2026-08-07T11:18:00.769993Z","submitted_at":"2026-01-18T17:17:31Z","title":"Video Individual Counting and Tracking from Moving Drones: A Benchmark and Methods","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-03T09:48:47.195038Z"},"links":{"citing_paper":"/paper/2601.12500"},"observation_digest":"sha256:efe18ffd8c1a9389ba26259187865cd65cb331cfc9d30f14585b90f98fd39272","observation_id":"39d2d5fe-0f1b-4d00-bc66-88fcba7834f2","resolution":{"observed_at":"2026-08-03T09:48:47.195038Z","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":"2026-08-03T09:48:47.370287Z","title":"Nwpu-crowd: A large-scale benchmark for crowd counting and localization,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2601.12500","last_updated":"2026-05-28T09:52:35Z","snapshot_observed_at":"2026-08-07T11:18:00.769993Z","submitted_at":"2026-01-18T17:17:31Z","title":"Video Individual Counting and Tracking from Moving Drones: A Benchmark and Methods","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-03T09:48:47.370287Z"},"links":{"citing_paper":"/paper/2601.12500"},"observation_digest":"sha256:a5b6e1698df1868851c6d141a7c779db0a0cf0b28839ad0aeceace5897aa5c57","observation_id":"ab2f6004-d16b-4f25-af36-ea5e18e5ad3a","resolution":{"observed_at":"2026-08-03T09:48:47.370287Z","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":"2026-08-03T09:48:47.515867Z","title":"Composition loss for counting, density map estimation and localization in dense crowds,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2601.12500","last_updated":"2026-05-28T09:52:35Z","snapshot_observed_at":"2026-08-07T11:18:00.769993Z","submitted_at":"2026-01-18T17:17:31Z","title":"Video Individual Counting and Tracking from Moving Drones: A Benchmark and Methods","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-03T09:48:47.515867Z"},"links":{"citing_paper":"/paper/2601.12500"},"observation_digest":"sha256:dc104feb3c51332068dd8aa459c95dead16e38d939a0e4773f12b0b024641069","observation_id":"2fc412be-df53-401c-b1c3-706655508b1d","resolution":{"observed_at":"2026-08-03T09:48:47.515867Z","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":"2026-08-03T09:48:47.653570Z","title":"Single-image crowd counting via multi-column convolutional neural network,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2601.12500","last_updated":"2026-05-28T09:52:35Z","snapshot_observed_at":"2026-08-07T11:18:00.769993Z","submitted_at":"2026-01-18T17:17:31Z","title":"Video Individual Counting and Tracking from Moving Drones: A Benchmark and Methods","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-03T09:48:47.653570Z"},"links":{"citing_paper":"/paper/2601.12500"},"observation_digest":"sha256:c86243ce89819184b203e8c7359a671401822cbc14dfb63c61045f02618f8b9b","observation_id":"07048071-5fd3-4290-bfcf-91e1853a696b","resolution":{"observed_at":"2026-08-03T09:48:47.653570Z","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":"2026-08-03T09:48:47.766580Z","title":"Multi-source multi-scale counting in extremely dense crowd images,","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2601.12500","last_updated":"2026-05-28T09:52:35Z","snapshot_observed_at":"2026-08-07T11:18:00.769993Z","submitted_at":"2026-01-18T17:17:31Z","title":"Video Individual Counting and Tracking from Moving Drones: A Benchmark and Methods","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-03T09:48:47.766580Z"},"links":{"citing_paper":"/paper/2601.12500"},"observation_digest":"sha256:f28c692113adb583277a200f2b4790349e4cfcd8e208b726c25a5b34a977d70a","observation_id":"3f6aaed4-a8fc-4eb5-b1e7-c54cdcfa96bf","resolution":{"observed_at":"2026-08-03T09:48:47.766580Z","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":"2026-08-03T09:48:47.911115Z","title":"Reducing spatial labeling redundancy for active semi-supervised crowd counting,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2601.12500","last_updated":"2026-05-28T09:52:35Z","snapshot_observed_at":"2026-08-07T11:18:00.769993Z","submitted_at":"2026-01-18T17:17:31Z","title":"Video Individual Counting and Tracking from Moving Drones: A Benchmark and Methods","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-03T09:48:47.911115Z"},"links":{"citing_paper":"/paper/2601.12500"},"observation_digest":"sha256:a3860ea1806db952216a2fbc29efff89b3bd204feb81ca94037f1070e16423e0","observation_id":"6987f96a-0abf-4dd8-9b81-3a83346311bf","resolution":{"observed_at":"2026-08-03T09:48:47.911115Z","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":"2026-08-03T09:48:48.021625Z","title":"Jhu-crowd++: Large-scale crowd counting dataset and a benchmark method,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2601.12500","last_updated":"2026-05-28T09:52:35Z","snapshot_observed_at":"2026-08-07T11:18:00.769993Z","submitted_at":"2026-01-18T17:17:31Z","title":"Video Individual Counting and Tracking from Moving Drones: A Benchmark and Methods","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-03T09:48:48.021625Z"},"links":{"citing_paper":"/paper/2601.12500"},"observation_digest":"sha256:e42b3ad4c496d2de5fea26572774873d4960c65bf046e04fa7222bed3e1d68f6","observation_id":"5c8334a0-17a8-4a4c-966a-bad462065b93","resolution":{"observed_at":"2026-08-03T09:48:48.021625Z","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":"2026-08-03T09:48:48.162011Z","title":"Point-to-region loss for semi-supervised point-based crowd counting,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2601.12500","last_updated":"2026-05-28T09:52:35Z","snapshot_observed_at":"2026-08-07T11:18:00.769993Z","submitted_at":"2026-01-18T17:17:31Z","title":"Video Individual Counting and Tracking from Moving Drones: A Benchmark and Methods","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-03T09:48:48.162011Z"},"links":{"citing_paper":"/paper/2601.12500"},"observation_digest":"sha256:a7b7a99bb6e5eb7a205c86620432005cc0578878797a01c3c7f2f25c12cd7482","observation_id":"5a8fa826-5f14-45e8-9030-4ac362a7e60f","resolution":{"observed_at":"2026-08-03T09:48:48.162011Z","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":"2026-08-03T09:48:48.308248Z","title":"Video crowd localization with multifocus gaussian neighborhood at- tention and a large-scale benchmark,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2601.12500","last_updated":"2026-05-28T09:52:35Z","snapshot_observed_at":"2026-08-07T11:18:00.769993Z","submitted_at":"2026-01-18T17:17:31Z","title":"Video Individual Counting and Tracking from Moving Drones: A Benchmark and Methods","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-03T09:48:48.308248Z"},"links":{"citing_paper":"/paper/2601.12500"},"observation_digest":"sha256:25669970c0e7af11e25597202c87149542d45a2c3dd9f8647abc1348766fac1c","observation_id":"59d22f3b-a5f6-4ed6-84a7-700c8a2c7d0c","resolution":{"observed_at":"2026-08-03T09:48:48.308248Z","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":"2026-08-03T09:48:48.479565Z","title":"Scene-adaptive unsupervised crowd counting for video surveillance,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2601.12500","last_updated":"2026-05-28T09:52:35Z","snapshot_observed_at":"2026-08-07T11:18:00.769993Z","submitted_at":"2026-01-18T17:17:31Z","title":"Video Individual Counting and Tracking from Moving Drones: A Benchmark and Methods","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-03T09:48:48.479565Z"},"links":{"citing_paper":"/paper/2601.12500"},"observation_digest":"sha256:ffd9397fff683e76b06e747088b3e573f939016043f1fca9825c60a7061f11c8","observation_id":"cd2f24e6-4443-491d-9f19-8443b4a833ed","resolution":{"observed_at":"2026-08-03T09:48:48.479565Z","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":"2026-08-03T09:48:48.601652Z","title":"Crowdcl: Unsupervised crowd counting network via contrastive learning,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2601.12500","last_updated":"2026-05-28T09:52:35Z","snapshot_observed_at":"2026-08-07T11:18:00.769993Z","submitted_at":"2026-01-18T17:17:31Z","title":"Video Individual Counting and Tracking from Moving Drones: A Benchmark and Methods","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-03T09:48:48.601652Z"},"links":{"citing_paper":"/paper/2601.12500"},"observation_digest":"sha256:3af40360b43ac8f674f8d5c81c775f347fdd747c1534099dab1761d83490172c","observation_id":"5d54f127-794b-42d7-a47a-d843a72be2c8","resolution":{"observed_at":"2026-08-03T09:48:48.601652Z","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":"2026-08-03T09:48:48.756318Z","title":"Dancetrack: Multi-object tracking in uniform appearance and diverse motion,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2601.12500","last_updated":"2026-05-28T09:52:35Z","snapshot_observed_at":"2026-08-07T11:18:00.769993Z","submitted_at":"2026-01-18T17:17:31Z","title":"Video Individual Counting and Tracking from Moving Drones: A Benchmark and Methods","version":2},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-03T09:48:48.756318Z"},"links":{"citing_paper":"/paper/2601.12500"},"observation_digest":"sha256:c32b30309373deb327aeddf6a56e4aa4a2920e58ba81d89ff3e2968726aca521","observation_id":"68dc8719-1e85-48e8-b135-b8f697198832","resolution":{"observed_at":"2026-08-03T09:48:48.756318Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2003.09003","last_updated":"2020-03-19T20:08:24Z","snapshot_observed_at":"2026-08-01T23:12:45.187111Z","submitted_at":"2020-03-19T20:08:24Z","title":"MOT20: A benchmark for multi object tracking in crowded scenes","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2003.09003","snapshot_observed_at":"2026-08-03T09:48:48.851639Z","title":"Mot20: A bench- mark for multi object tracking in crowded scenes,","venue":null,"work_id":null,"year":2003},"citing_paper":{"arxiv_id":"2601.12500","last_updated":"2026-05-28T09:52:35Z","snapshot_observed_at":"2026-08-07T11:18:00.769993Z","submitted_at":"2026-01-18T17:17:31Z","title":"Video Individual Counting and Tracking from Moving Drones: A Benchmark and Methods","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-03T09:48:48.851639Z"},"links":{"cited_paper":"/paper/2003.09003","citing_paper":"/paper/2601.12500"},"observation_digest":"sha256:2558d577f51dd8287e914cd0c82231609a8408acc0d41e16fb9015733a5901d4","observation_id":"dda19067-8d15-4b60-8e29-2c63d882edc6","resolution":{"observed_at":"2026-08-03T09:48:48.851639Z","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":"2026-08-03T09:48:48.989483Z","title":"Sportsmot: A large multi-object tracking dataset in multiple sports scenes,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2601.12500","last_updated":"2026-05-28T09:52:35Z","snapshot_observed_at":"2026-08-07T11:18:00.769993Z","submitted_at":"2026-01-18T17:17:31Z","title":"Video Individual Counting and Tracking from Moving Drones: A Benchmark and Methods","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-03T09:48:48.989483Z"},"links":{"citing_paper":"/paper/2601.12500"},"observation_digest":"sha256:cf2dc10c51d5301eda2123490e409181fd63e107352d9d0c8f938a84b3c19cab","observation_id":"f81bad3a-e8c0-4ad8-bd00-35333eb3bb18","resolution":{"observed_at":"2026-08-03T09:48:48.989483Z","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":"2026-08-03T09:48:49.111162Z","title":"Crowded video individual counting informed by social grouping and spatial-temporal displacement priors,","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2601.12500","last_updated":"2026-05-28T09:52:35Z","snapshot_observed_at":"2026-08-07T11:18:00.769993Z","submitted_at":"2026-01-18T17:17:31Z","title":"Video Individual Counting and Tracking from Moving Drones: A Benchmark and Methods","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-03T09:48:49.111162Z"},"links":{"citing_paper":"/paper/2601.12500"},"observation_digest":"sha256:a0b6ff7c451087b4a99723731a672f1785fc04f1a1277a690640571d3746a3f3","observation_id":"2781fb8e-0793-476f-b62f-d36f157feb69","resolution":{"observed_at":"2026-08-03T09:48:49.111162Z","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":"2026-08-03T09:48:49.205995Z","title":"Detection, tracking, and counting meets drones in crowds: A benchmark,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2601.12500","last_updated":"2026-05-28T09:52:35Z","snapshot_observed_at":"2026-08-07T11:18:00.769993Z","submitted_at":"2026-01-18T17:17:31Z","title":"Video Individual Counting and Tracking from Moving Drones: A Benchmark and Methods","version":2},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-03T09:48:49.205995Z"},"links":{"citing_paper":"/paper/2601.12500"},"observation_digest":"sha256:646d5436801787b3f5f74fff420d10af11b3ae2cb8003478893074326494ae3c","observation_id":"5e358909-68f0-4d66-8a61-b46792497138","resolution":{"observed_at":"2026-08-03T09:48:49.205995Z","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":"2026-08-03T09:48:49.348471Z","title":"Visdrone-cc2021: The vision meets drone crowd counting challenge results,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2601.12500","last_updated":"2026-05-28T09:52:35Z","snapshot_observed_at":"2026-08-07T11:18:00.769993Z","submitted_at":"2026-01-18T17:17:31Z","title":"Video Individual Counting and Tracking from Moving Drones: A Benchmark and Methods","version":2},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-03T09:48:49.348471Z"},"links":{"citing_paper":"/paper/2601.12500"},"observation_digest":"sha256:ce0320c4fc80e420e22139a2f43bacba2f97065d1bfdddd881739bd85a33a1f3","observation_id":"6bc0f2f6-931b-4eb5-be19-efb2df50d9a4","resolution":{"observed_at":"2026-08-03T09:48:49.348471Z","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":"2026-08-03T09:48:49.479148Z","title":"Weakly supervised video individual counting,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2601.12500","last_updated":"2026-05-28T09:52:35Z","snapshot_observed_at":"2026-08-07T11:18:00.769993Z","submitted_at":"2026-01-18T17:17:31Z","title":"Video Individual Counting and Tracking from Moving Drones: A Benchmark and Methods","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-03T09:48:49.479148Z"},"links":{"citing_paper":"/paper/2601.12500"},"observation_digest":"sha256:c0c71d42303872978c71fcc5d763ef20b7dbd9447e50aae0ddc2f62540a6b61b","observation_id":"a6e53e5a-31c4-41a0-a5ac-47f11a391c0b","resolution":{"observed_at":"2026-08-03T09:48:49.479148Z","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":"2026-08-03T09:48:49.577306Z","title":"Detection and tracking meet drones challenge,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2601.12500","last_updated":"2026-05-28T09:52:35Z","snapshot_observed_at":"2026-08-07T11:18:00.769993Z","submitted_at":"2026-01-18T17:17:31Z","title":"Video Individual Counting and Tracking from Moving Drones: A Benchmark and Methods","version":2},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-03T09:48:49.577306Z"},"links":{"citing_paper":"/paper/2601.12500"},"observation_digest":"sha256:25533fa4f639d0d713eab6e1be460478a9b1691a1865a73b165ccc816d8f3d16","observation_id":"486e2265-f3ea-4a6f-8b10-7f6541dd9c89","resolution":{"observed_at":"2026-08-03T09:48:49.577306Z","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":"2026-08-03T09:48:49.699978Z","title":"Bytetrack: Multi-object tracking by associating every detection box,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2601.12500","last_updated":"2026-05-28T09:52:35Z","snapshot_observed_at":"2026-08-07T11:18:00.769993Z","submitted_at":"2026-01-18T17:17:31Z","title":"Video Individual Counting and Tracking from Moving Drones: A Benchmark and Methods","version":2},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-03T09:48:49.699978Z"},"links":{"citing_paper":"/paper/2601.12500"},"observation_digest":"sha256:69d91b92e18e4bbf37e69fa8a8ba265c88656a35f85d3348f6caa9cc7f41472d","observation_id":"065d6a65-79ea-4a92-9ed2-0c31adb572cc","resolution":{"observed_at":"2026-08-03T09:48:49.699978Z","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":"2026-08-03T09:48:49.860754Z","title":"Track- former: Multi-object tracking with transformers,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2601.12500","last_updated":"2026-05-28T09:52:35Z","snapshot_observed_at":"2026-08-07T11:18:00.769993Z","submitted_at":"2026-01-18T17:17:31Z","title":"Video Individual Counting and Tracking from Moving Drones: A Benchmark and Methods","version":2},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-03T09:48:49.860754Z"},"links":{"citing_paper":"/paper/2601.12500"},"observation_digest":"sha256:0ee5aa822b6ec1ab0562df4cda4b0b20d24447b580dc42d7aa9b7bc07c08b5ab","observation_id":"f6d74232-447f-4291-956b-2ebfca8b16fc","resolution":{"observed_at":"2026-08-03T09:48:49.860754Z","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":"2026-08-03T09:48:50.015954Z","title":"Sparsetrack: Multi- object tracking by performing scene decomposition based on pseudo- depth,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2601.12500","last_updated":"2026-05-28T09:52:35Z","snapshot_observed_at":"2026-08-07T11:18:00.769993Z","submitted_at":"2026-01-18T17:17:31Z","title":"Video Individual Counting and Tracking from Moving Drones: A Benchmark and Methods","version":2},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-03T09:48:50.015954Z"},"links":{"citing_paper":"/paper/2601.12500"},"observation_digest":"sha256:5abfc02ed314eee7527d702f817e9450962d6011313c100269dadd9dff517a76","observation_id":"12a9aa6e-248f-4d58-8227-c121b271544f","resolution":{"observed_at":"2026-08-03T09:48:50.015954Z","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":"2026-08-03T09:48:50.114197Z","title":"Multi-object tracking in the dark,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2601.12500","last_updated":"2026-05-28T09:52:35Z","snapshot_observed_at":"2026-08-07T11:18:00.769993Z","submitted_at":"2026-01-18T17:17:31Z","title":"Video Individual Counting and Tracking from Moving Drones: A Benchmark and Methods","version":2},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-03T09:48:50.114197Z"},"links":{"citing_paper":"/paper/2601.12500"},"observation_digest":"sha256:f452cbbe25e9e1a0969d6ad005fb2682d101ae64884719334c85fe5a580b2cde","observation_id":"cb123103-e1d5-457f-a7a7-36e60b8f22b7","resolution":{"observed_at":"2026-08-03T09:48:50.114197Z","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":"2026-08-03T09:48:50.229036Z","title":"Diffusiontrack: Diffusion model for multi-object tracking,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2601.12500","last_updated":"2026-05-28T09:52:35Z","snapshot_observed_at":"2026-08-07T11:18:00.769993Z","submitted_at":"2026-01-18T17:17:31Z","title":"Video Individual Counting and Tracking from Moving Drones: A Benchmark and Methods","version":2},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-03T09:48:50.229036Z"},"links":{"citing_paper":"/paper/2601.12500"},"observation_digest":"sha256:85a540d08d84968d4bc90a5bdb6e605afa058fac6e5cdca55cc6a4368498be76","observation_id":"c5cf36bd-c064-4e89-aa63-b9f97593b0e7","resolution":{"observed_at":"2026-08-03T09:48:50.229036Z","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":"2026-08-03T09:48:50.333604Z","title":"Dr.vic: Decompo- sition and reasoning for video individual counting,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2601.12500","last_updated":"2026-05-28T09:52:35Z","snapshot_observed_at":"2026-08-07T11:18:00.769993Z","submitted_at":"2026-01-18T17:17:31Z","title":"Video Individual Counting and Tracking from Moving Drones: A Benchmark and Methods","version":2},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-03T09:48:50.333604Z"},"links":{"citing_paper":"/paper/2601.12500"},"observation_digest":"sha256:0190954929844c9a8418ed17912aa751dc72ee5e9c59eeb7b4f2aa230ffb87c4","observation_id":"481601f9-56ac-4c68-8e60-93510f548a0d","resolution":{"observed_at":"2026-08-03T09:48:50.333604Z","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":"2026-08-03T09:48:50.412969Z","title":"Prototype-guided dual- transformer reasoning for video individual counting,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2601.12500","last_updated":"2026-05-28T09:52:35Z","snapshot_observed_at":"2026-08-07T11:18:00.769993Z","submitted_at":"2026-01-18T17:17:31Z","title":"Video Individual Counting and Tracking from Moving Drones: A Benchmark and Methods","version":2},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-03T09:48:50.412969Z"},"links":{"citing_paper":"/paper/2601.12500"},"observation_digest":"sha256:51199d85328a3adbcfb879b32eddef9cadad47f82603bd6d24b2c499f71e4d2f","observation_id":"f1e3329f-766e-43a2-b507-42def813a8fa","resolution":{"observed_at":"2026-08-03T09:48:50.412969Z","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":"2026-08-03T09:48:50.545644Z","title":"Video individual counting for moving drones,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2601.12500","last_updated":"2026-05-28T09:52:35Z","snapshot_observed_at":"2026-08-07T11:18:00.769993Z","submitted_at":"2026-01-18T17:17:31Z","title":"Video Individual Counting and Tracking from Moving Drones: A Benchmark and Methods","version":2},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-03T09:48:50.545644Z"},"links":{"citing_paper":"/paper/2601.12500"},"observation_digest":"sha256:e282a8c66245d846cc55ce5d1b7c7cfb307eb68ad69345bc4f31158d097047d1","observation_id":"e39dbf7e-eb25-4f2d-9be9-2c36a312e807","resolution":{"observed_at":"2026-08-03T09:48:50.545644Z","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":"2026-08-03T09:48:50.678078Z","title":"Density-based flow mask in- tegration via deformable convolution for video people flux estimation,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2601.12500","last_updated":"2026-05-28T09:52:35Z","snapshot_observed_at":"2026-08-07T11:18:00.769993Z","submitted_at":"2026-01-18T17:17:31Z","title":"Video Individual Counting and Tracking from Moving Drones: A Benchmark and Methods","version":2},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-03T09:48:50.678078Z"},"links":{"citing_paper":"/paper/2601.12500"},"observation_digest":"sha256:7444bad0d23d68aff1f9ccfab75a2092276c3ca032844cc7feacd9586c9a5935","observation_id":"86231a17-2728-4dd4-9d7b-7f3aa522662d","resolution":{"observed_at":"2026-08-03T09:48:50.678078Z","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":"2026-08-03T09:48:50.766738Z","title":"Flowing crowd to count flows: A self-supervised frame- work for video individual counting,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2601.12500","last_updated":"2026-05-28T09:52:35Z","snapshot_observed_at":"2026-08-07T11:18:00.769993Z","submitted_at":"2026-01-18T17:17:31Z","title":"Video Individual Counting and Tracking from Moving Drones: A Benchmark and Methods","version":2},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-03T09:48:50.766738Z"},"links":{"citing_paper":"/paper/2601.12500"},"observation_digest":"sha256:a7acf8e8cb7827c022a8a0c2421a353e35e4f5048d355161db0e2452b812f528","observation_id":"013822e6-38e5-4eba-a883-f92843a436ef","resolution":{"observed_at":"2026-08-03T09:48:50.766738Z","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":"2026-08-03T09:48:50.875335Z","title":"Context-aware crowd counting,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2601.12500","last_updated":"2026-05-28T09:52:35Z","snapshot_observed_at":"2026-08-07T11:18:00.769993Z","submitted_at":"2026-01-18T17:17:31Z","title":"Video Individual Counting and Tracking from Moving Drones: A Benchmark and Methods","version":2},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-03T09:48:50.875335Z"},"links":{"citing_paper":"/paper/2601.12500"},"observation_digest":"sha256:724fa3e20d46f19ad36d09ab995e78ccb76a7705d9844da2470d2fa729662796","observation_id":"7d03e310-e704-4cf4-8d7b-8539cb3c7275","resolution":{"observed_at":"2026-08-03T09:48:50.875335Z","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":"2026-08-03T09:48:51.015601Z","title":"Reverse perspec- tive network for perspective-aware object counting,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2601.12500","last_updated":"2026-05-28T09:52:35Z","snapshot_observed_at":"2026-08-07T11:18:00.769993Z","submitted_at":"2026-01-18T17:17:31Z","title":"Video Individual Counting and Tracking from Moving Drones: A Benchmark and Methods","version":2},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-03T09:48:51.015601Z"},"links":{"citing_paper":"/paper/2601.12500"},"observation_digest":"sha256:8d684a86d4c41516e45b1f0f5572aeb4dc1ea8b192108df240e8239424881ef4","observation_id":"753047da-459b-4694-8b42-81737809c6c1","resolution":{"observed_at":"2026-08-03T09:48:51.015601Z","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":"2026-08-03T09:48:51.177497Z","title":"Distribution matching for crowd counting,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2601.12500","last_updated":"2026-05-28T09:52:35Z","snapshot_observed_at":"2026-08-07T11:18:00.769993Z","submitted_at":"2026-01-18T17:17:31Z","title":"Video Individual Counting and Tracking from Moving Drones: A Benchmark and Methods","version":2},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-03T09:48:51.177497Z"},"links":{"citing_paper":"/paper/2601.12500"},"observation_digest":"sha256:c91a55011f1f7cd0125abd513aefc985ca94f99ec96a317737e853cede79bb5a","observation_id":"868f487f-366f-4312-8c97-cde4506400d1","resolution":{"observed_at":"2026-08-03T09:48:51.177497Z","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":"2026-08-03T09:48:51.345679Z","title":"Steerer: Resolving scale varia- tions for counting and localization via selective inheritance learning,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2601.12500","last_updated":"2026-05-28T09:52:35Z","snapshot_observed_at":"2026-08-07T11:18:00.769993Z","submitted_at":"2026-01-18T17:17:31Z","title":"Video Individual Counting and Tracking from Moving Drones: A Benchmark and Methods","version":2},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-03T09:48:51.345679Z"},"links":{"citing_paper":"/paper/2601.12500"},"observation_digest":"sha256:78ad44a3c3b036b8a45773117e48bd0fbef53d03ee4703088fb1ec88c7172335","observation_id":"e2d0465a-6d12-4c1a-8ef7-2bb51738369c","resolution":{"observed_at":"2026-08-03T09:48:51.345679Z","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":"2026-08-03T09:48:51.488642Z","title":"Crowddiff: Multi-hypothesis crowd density estimation using diffusion models,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2601.12500","last_updated":"2026-05-28T09:52:35Z","snapshot_observed_at":"2026-08-07T11:18:00.769993Z","submitted_at":"2026-01-18T17:17:31Z","title":"Video Individual Counting and Tracking from Moving Drones: A Benchmark and Methods","version":2},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-03T09:48:51.488642Z"},"links":{"citing_paper":"/paper/2601.12500"},"observation_digest":"sha256:3b83122cf863c1425ebbb4ae74f241f0d9d3b62a9234eea44001cf58996e7d6a","observation_id":"07e07713-8984-434e-a4bc-fb8c91d5c955","resolution":{"observed_at":"2026-08-03T09:48:51.488642Z","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":"2026-08-03T09:48:51.647439Z","title":"Face recognition using kernel ridge regression,","venue":null,"work_id":null,"year":2007},"citing_paper":{"arxiv_id":"2601.12500","last_updated":"2026-05-28T09:52:35Z","snapshot_observed_at":"2026-08-07T11:18:00.769993Z","submitted_at":"2026-01-18T17:17:31Z","title":"Video Individual Counting and Tracking from Moving Drones: A Benchmark and Methods","version":2},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-03T09:48:51.647439Z"},"links":{"citing_paper":"/paper/2601.12500"},"observation_digest":"sha256:a139f1ac679706dfe02d022a5039c3ed61c0a9724d710b72184e504a0db6e28d","observation_id":"a1f740f7-09e2-44fa-8ba7-6376e34b7dfc","resolution":{"observed_at":"2026-08-03T09:48:51.647439Z","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":"2026-08-03T09:48:51.758637Z","title":"Crowd density estimation using texture analysis and learning,","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2601.12500","last_updated":"2026-05-28T09:52:35Z","snapshot_observed_at":"2026-08-07T11:18:00.769993Z","submitted_at":"2026-01-18T17:17:31Z","title":"Video Individual Counting and Tracking from Moving Drones: A Benchmark and Methods","version":2},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-03T09:48:51.758637Z"},"links":{"citing_paper":"/paper/2601.12500"},"observation_digest":"sha256:c9ef945dae1e51a50e6548e37293389896f664290c8a8fe535888ee4594f7937","observation_id":"97d168aa-8fd6-47e1-b1ff-3a9ded85efc2","resolution":{"observed_at":"2026-08-03T09:48:51.758637Z","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":"2026-08-03T09:48:51.902634Z","title":"Privacy preserving crowd monitoring: Counting people without people models or tracking,","venue":null,"work_id":null,"year":2008},"citing_paper":{"arxiv_id":"2601.12500","last_updated":"2026-05-28T09:52:35Z","snapshot_observed_at":"2026-08-07T11:18:00.769993Z","submitted_at":"2026-01-18T17:17:31Z","title":"Video Individual Counting and Tracking from Moving Drones: A Benchmark and Methods","version":2},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-03T09:48:51.902634Z"},"links":{"citing_paper":"/paper/2601.12500"},"observation_digest":"sha256:49f924836c4f7478fd368b9dd7d518d39f5e01306c22ba5e7d90f495d2b38ec6","observation_id":"8c2b64e2-82e8-4ed4-9d56-57330b86ba11","resolution":{"observed_at":"2026-08-03T09:48:51.902634Z","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":"2026-08-03T09:48:52.032198Z","title":"Deep people counting in extremely dense crowds,","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2601.12500","last_updated":"2026-05-28T09:52:35Z","snapshot_observed_at":"2026-08-07T11:18:00.769993Z","submitted_at":"2026-01-18T17:17:31Z","title":"Video Individual Counting and Tracking from Moving Drones: A Benchmark and Methods","version":2},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-03T09:48:52.032198Z"},"links":{"citing_paper":"/paper/2601.12500"},"observation_digest":"sha256:6723ab786a892b42f6f60f64fcd0347a86a4aa9e5fefc945b2b1ea375966266c","observation_id":"1fd84fb3-0ee8-4541-b14a-649d5f45af2a","resolution":{"observed_at":"2026-08-03T09:48:52.032198Z","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":"2026-08-03T09:48:52.129785Z","title":"Revisiting perspective infor- mation for efficient crowd counting,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2601.12500","last_updated":"2026-05-28T09:52:35Z","snapshot_observed_at":"2026-08-07T11:18:00.769993Z","submitted_at":"2026-01-18T17:17:31Z","title":"Video Individual Counting and Tracking from Moving Drones: A Benchmark and Methods","version":2},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-03T09:48:52.129785Z"},"links":{"citing_paper":"/paper/2601.12500"},"observation_digest":"sha256:58e9c8c116c2f7008b01bd0ae4ae02f4d8194839783f5943a9149f81df1e9303","observation_id":"274c78cb-83a6-443a-a494-881465ec5ab8","resolution":{"observed_at":"2026-08-03T09:48:52.129785Z","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":"2026-08-03T09:48:52.255579Z","title":"Perspective-guided convolution networks for crowd counting,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2601.12500","last_updated":"2026-05-28T09:52:35Z","snapshot_observed_at":"2026-08-07T11:18:00.769993Z","submitted_at":"2026-01-18T17:17:31Z","title":"Video Individual Counting and Tracking from Moving Drones: A Benchmark and Methods","version":2},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-03T09:48:52.255579Z"},"links":{"citing_paper":"/paper/2601.12500"},"observation_digest":"sha256:8c7bd397121b6200591ca4e76a8f7faba19e235d8f2258d57f5f746ec526f5fb","observation_id":"de7647af-8365-49fd-99a7-9f66e6e6e33b","resolution":{"observed_at":"2026-08-03T09:48:52.255579Z","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":"2026-08-03T09:48:52.349061Z","title":"Redesigning multi-scale neural network for crowd counting,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2601.12500","last_updated":"2026-05-28T09:52:35Z","snapshot_observed_at":"2026-08-07T11:18:00.769993Z","submitted_at":"2026-01-18T17:17:31Z","title":"Video Individual Counting and Tracking from Moving Drones: A Benchmark and Methods","version":2},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-03T09:48:52.349061Z"},"links":{"citing_paper":"/paper/2601.12500"},"observation_digest":"sha256:0fca41b4b70187ff4d9b751833a0861261745a0ebeef73e84f8d4ee56370100c","observation_id":"9dea0d16-dc77-44ca-bb3f-ffea74a6678d","resolution":{"observed_at":"2026-08-03T09:48:52.349061Z","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":"2026-08-03T09:48:52.507491Z","title":"Stnet: Scale tree network with multi-level auxiliator for crowd counting,","venue":null,"work_id":null,"year":2074},"citing_paper":{"arxiv_id":"2601.12500","last_updated":"2026-05-28T09:52:35Z","snapshot_observed_at":"2026-08-07T11:18:00.769993Z","submitted_at":"2026-01-18T17:17:31Z","title":"Video Individual Counting and Tracking from Moving Drones: A Benchmark and Methods","version":2},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-03T09:48:52.507491Z"},"links":{"citing_paper":"/paper/2601.12500"},"observation_digest":"sha256:0124f258cf9757d52fa6633f481d5b40065ab92c8a99e0c5910e5981fd21ffed","observation_id":"b84d65cc-3f1d-4e95-b636-82af46386950","resolution":{"observed_at":"2026-08-03T09:48:52.507491Z","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":"2026-08-03T09:48:52.719853Z","title":"Domain-adaptive crowd counting via high-quality image translation and density reconstruction,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2601.12500","last_updated":"2026-05-28T09:52:35Z","snapshot_observed_at":"2026-08-07T11:18:00.769993Z","submitted_at":"2026-01-18T17:17:31Z","title":"Video Individual Counting and Tracking from Moving Drones: A Benchmark and Methods","version":2},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-03T09:48:52.719853Z"},"links":{"citing_paper":"/paper/2601.12500"},"observation_digest":"sha256:282e23de3e9d43e48847a992580046d6800afb00f9bbff782d6cc021c0c7873b","observation_id":"0037447d-77bf-4a57-a927-e8e95e3f453b","resolution":{"observed_at":"2026-08-03T09:48:52.719853Z","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":"2026-08-03T09:48:52.856147Z","title":"Domain-general crowd counting in unseen scenarios,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2601.12500","last_updated":"2026-05-28T09:52:35Z","snapshot_observed_at":"2026-08-07T11:18:00.769993Z","submitted_at":"2026-01-18T17:17:31Z","title":"Video Individual Counting and Tracking from Moving Drones: A Benchmark and Methods","version":2},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-03T09:48:52.856147Z"},"links":{"citing_paper":"/paper/2601.12500"},"observation_digest":"sha256:cbc2e11eaba4d09ffde6bc7130e36bded92a2359177cafa4d56c9a84e11558a1","observation_id":"391840df-5bdb-4957-81be-93b37b1dc601","resolution":{"observed_at":"2026-08-03T09:48:52.856147Z","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":"2026-08-03T09:48:52.982093Z","title":"Striking a balance: Unsu- pervised cross-domain crowd counting via knowledge diffusion,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2601.12500","last_updated":"2026-05-28T09:52:35Z","snapshot_observed_at":"2026-08-07T11:18:00.769993Z","submitted_at":"2026-01-18T17:17:31Z","title":"Video Individual Counting and Tracking from Moving Drones: A Benchmark and Methods","version":2},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-03T09:48:52.982093Z"},"links":{"citing_paper":"/paper/2601.12500"},"observation_digest":"sha256:527f6c532b56505a05a8ad1eca3a712ac95b1af7f07b13875b630123489879e4","observation_id":"08150602-c777-4079-9b8f-76d97e1366aa","resolution":{"observed_at":"2026-08-03T09:48:52.982093Z","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":"2026-08-03T09:48:53.122813Z","title":"Bi-level alignment for cross-domain crowd counting,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2601.12500","last_updated":"2026-05-28T09:52:35Z","snapshot_observed_at":"2026-08-07T11:18:00.769993Z","submitted_at":"2026-01-18T17:17:31Z","title":"Video Individual Counting and Tracking from Moving Drones: A Benchmark and Methods","version":2},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-03T09:48:53.122813Z"},"links":{"citing_paper":"/paper/2601.12500"},"observation_digest":"sha256:79f678940761f2511db1039ba2b43f25c2c8f04cf8247b7d2d852fdcd2bf1fd2","observation_id":"bf15a35b-fd17-4f2c-8c67-075cf4b68d75","resolution":{"observed_at":"2026-08-03T09:48:53.122813Z","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":"2026-08-03T09:48:53.261210Z","title":"A generalized loss function for crowd counting and localization,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2601.12500","last_updated":"2026-05-28T09:52:35Z","snapshot_observed_at":"2026-08-07T11:18:00.769993Z","submitted_at":"2026-01-18T17:17:31Z","title":"Video Individual Counting and Tracking from Moving Drones: A Benchmark and Methods","version":2},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-03T09:48:53.261210Z"},"links":{"citing_paper":"/paper/2601.12500"},"observation_digest":"sha256:5f38213eb6d096f8513ab9bb540d024f1e492a443988ff90a883153a2ce54eaf","observation_id":"5ee246b4-3e46-4ac5-8cd0-1fc36d252d11","resolution":{"observed_at":"2026-08-03T09:48:53.261210Z","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":"2026-08-03T09:48:53.350350Z","title":"Bayesian poisson regression for crowd counting,","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2601.12500","last_updated":"2026-05-28T09:52:35Z","snapshot_observed_at":"2026-08-07T11:18:00.769993Z","submitted_at":"2026-01-18T17:17:31Z","title":"Video Individual Counting and Tracking from Moving Drones: A Benchmark and Methods","version":2},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-03T09:48:53.350350Z"},"links":{"citing_paper":"/paper/2601.12500"},"observation_digest":"sha256:ecee8993e9900dd6e92deed9c42d058dc4be80c592281966ae788b803837315d","observation_id":"9d72174e-b79b-40d6-922f-c95594b3f03f","resolution":{"observed_at":"2026-08-03T09:48:53.350350Z","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":"2026-08-03T09:48:53.423047Z","title":"An end-to-end transformer model for crowd localization,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2601.12500","last_updated":"2026-05-28T09:52:35Z","snapshot_observed_at":"2026-08-07T11:18:00.769993Z","submitted_at":"2026-01-18T17:17:31Z","title":"Video Individual Counting and Tracking from Moving Drones: A Benchmark and Methods","version":2},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-03T09:48:53.423047Z"},"links":{"citing_paper":"/paper/2601.12500"},"observation_digest":"sha256:f7baa34407de94078368d3a58204f82b20efb0498d414c6cc7da75cfd6c8d908","observation_id":"812b23f5-d806-4aae-a8f3-b9f6a2d70629","resolution":{"observed_at":"2026-08-03T09:48:53.423047Z","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":"2026-08-03T09:48:53.466155Z","title":"Learning crowd scale and distribution for weakly supervised crowd counting and localization,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2601.12500","last_updated":"2026-05-28T09:52:35Z","snapshot_observed_at":"2026-08-07T11:18:00.769993Z","submitted_at":"2026-01-18T17:17:31Z","title":"Video Individual Counting and Tracking from Moving Drones: A Benchmark and Methods","version":2},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-03T09:48:53.466155Z"},"links":{"citing_paper":"/paper/2601.12500"},"observation_digest":"sha256:07d7e294887373507d49ce12fa9351486e434485cc65bdf5d320e1ee1d22a1fe","observation_id":"e5f78499-10e3-478f-aa3b-bc9ca553edbc","resolution":{"observed_at":"2026-08-03T09:48:53.466155Z","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":"2026-08-03T09:48:53.522806Z","title":"Delving into the trajectory long-tail distribution for muti-object tracking,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2601.12500","last_updated":"2026-05-28T09:52:35Z","snapshot_observed_at":"2026-08-07T11:18:00.769993Z","submitted_at":"2026-01-18T17:17:31Z","title":"Video Individual Counting and Tracking from Moving Drones: A Benchmark and Methods","version":2},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-03T09:48:53.522806Z"},"links":{"citing_paper":"/paper/2601.12500"},"observation_digest":"sha256:0393297b0bff97003f63033978a8e41fe93828720b75c2e621d9b1ef3ba58bf0","observation_id":"f9852284-e82d-4cb6-92f4-97e88170564e","resolution":{"observed_at":"2026-08-03T09:48:53.522806Z","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":"2026-08-03T09:48:53.638021Z","title":"Deconfusetrack: Dealing with confusion for multi-object tracking,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2601.12500","last_updated":"2026-05-28T09:52:35Z","snapshot_observed_at":"2026-08-07T11:18:00.769993Z","submitted_at":"2026-01-18T17:17:31Z","title":"Video Individual Counting and Tracking from Moving Drones: A Benchmark and Methods","version":2},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-03T09:48:53.638021Z"},"links":{"citing_paper":"/paper/2601.12500"},"observation_digest":"sha256:6b97088031c368c2d4f9c50a3a04f782248318b67104a66c8eb708e5dede8377","observation_id":"548e2a36-0b67-468a-a609-7cb51bb54ea7","resolution":{"observed_at":"2026-08-03T09:48:53.638021Z","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":"2026-08-03T09:48:53.785694Z","title":"Utm: A unified multiple object tracking model with identity-aware feature enhancement,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2601.12500","last_updated":"2026-05-28T09:52:35Z","snapshot_observed_at":"2026-08-07T11:18:00.769993Z","submitted_at":"2026-01-18T17:17:31Z","title":"Video Individual Counting and Tracking from Moving Drones: A Benchmark and Methods","version":2},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-03T09:48:53.785694Z"},"links":{"citing_paper":"/paper/2601.12500"},"observation_digest":"sha256:e5fcd57de8965193cf2e1168d2c11d7682bfa6ce3128c73aec844af783165d9a","observation_id":"9c051e32-2d92-45ca-ac28-b74420444b6d","resolution":{"observed_at":"2026-08-03T09:48:53.785694Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2206.14651","last_updated":"2022-07-07T15:36:49Z","snapshot_observed_at":"2026-08-06T22:11:02.627602Z","submitted_at":"2022-06-29T13:45:03Z","title":"BoT-SORT: Robust Associations Multi-Pedestrian Tracking","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2206.14651","snapshot_observed_at":"2026-08-03T09:48:53.818765Z","title":"Bot-sort: Robust asso- ciations multi-pedestrian tracking,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2601.12500","last_updated":"2026-05-28T09:52:35Z","snapshot_observed_at":"2026-08-07T11:18:00.769993Z","submitted_at":"2026-01-18T17:17:31Z","title":"Video Individual Counting and Tracking from Moving Drones: A Benchmark and Methods","version":2},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-03T09:48:53.818765Z"},"links":{"cited_paper":"/paper/2206.14651","citing_paper":"/paper/2601.12500"},"observation_digest":"sha256:b5dd68414795ba3a4bc56ea1bcd3eedb96c871a68f2f3466ae13f5dceff2d8df","observation_id":"d762ea8d-7914-4ac0-a6b3-b39caef349bb","resolution":{"observed_at":"2026-08-03T09:48:53.818765Z","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":"2026-08-03T09:48:53.954146Z","title":"Diffmot: A real-time diffusion-based multiple object tracker with non-linear prediction,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2601.12500","last_updated":"2026-05-28T09:52:35Z","snapshot_observed_at":"2026-08-07T11:18:00.769993Z","submitted_at":"2026-01-18T17:17:31Z","title":"Video Individual Counting and Tracking from Moving Drones: A Benchmark and Methods","version":2},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-03T09:48:53.954146Z"},"links":{"citing_paper":"/paper/2601.12500"},"observation_digest":"sha256:553d87aefc27ebac2e681b4b641dbcfd922684893dd068eb2525e20bc16d94cd","observation_id":"5703a0b6-3327-4e8f-805f-e631040231bf","resolution":{"observed_at":"2026-08-03T09:48:53.954146Z","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":"2026-08-03T09:48:54.050841Z","title":"Observation- centric sort: Rethinking sort for robust multi-object tracking,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2601.12500","last_updated":"2026-05-28T09:52:35Z","snapshot_observed_at":"2026-08-07T11:18:00.769993Z","submitted_at":"2026-01-18T17:17:31Z","title":"Video Individual Counting and Tracking from Moving Drones: A Benchmark and Methods","version":2},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-03T09:48:54.050841Z"},"links":{"citing_paper":"/paper/2601.12500"},"observation_digest":"sha256:7989e428e52ee528ad9ba8a80c6c93d52e7ceb11b66bb41e20788ec839b205ca","observation_id":"3418ba5e-2cff-43aa-9865-24b7f3c2a17b","resolution":{"observed_at":"2026-08-03T09:48:54.050841Z","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":"2026-08-03T09:48:54.178219Z","title":"A new approach to linear filtering and prediction problems,","venue":null,"work_id":null,"year":1960},"citing_paper":{"arxiv_id":"2601.12500","last_updated":"2026-05-28T09:52:35Z","snapshot_observed_at":"2026-08-07T11:18:00.769993Z","submitted_at":"2026-01-18T17:17:31Z","title":"Video Individual Counting and Tracking from Moving Drones: A Benchmark and Methods","version":2},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-03T09:48:54.178219Z"},"links":{"citing_paper":"/paper/2601.12500"},"observation_digest":"sha256:f3b58e572aae7af8623eb50733dcb253dc61f718ad6f91580530c48f01807d08","observation_id":"fbbefa88-82ab-4d19-9d41-b0bf83e8e0fb","resolution":{"observed_at":"2026-08-03T09:48:54.178219Z","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":"2026-08-03T09:48:54.280392Z","title":"Motr: End-to-end multiple-object tracking with transformer,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2601.12500","last_updated":"2026-05-28T09:52:35Z","snapshot_observed_at":"2026-08-07T11:18:00.769993Z","submitted_at":"2026-01-18T17:17:31Z","title":"Video Individual Counting and Tracking from Moving Drones: A Benchmark and Methods","version":2},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-03T09:48:54.280392Z"},"links":{"citing_paper":"/paper/2601.12500"},"observation_digest":"sha256:043b2f61b751d7e5fc575da6e30ccf2fc3110b44a96cb9dad6be0f2ae91bd0ff","observation_id":"af79a563-b426-4e75-aabe-6e5f4ce49c18","resolution":{"observed_at":"2026-08-03T09:48:54.280392Z","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":"2026-08-03T09:48:54.402248Z","title":"Rgb-t crowd counting from drone: A benchmark and mmccn network,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2601.12500","last_updated":"2026-05-28T09:52:35Z","snapshot_observed_at":"2026-08-07T11:18:00.769993Z","submitted_at":"2026-01-18T17:17:31Z","title":"Video Individual Counting and Tracking from Moving Drones: A Benchmark and Methods","version":2},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-03T09:48:54.402248Z"},"links":{"citing_paper":"/paper/2601.12500"},"observation_digest":"sha256:92d72ef5800c1e451fcfac885c585460f2c2fb32891629aaf0b84871c5e4379a","observation_id":"7edd5f54-5c97-4c17-ae50-2ef6e19ffd98","resolution":{"observed_at":"2026-08-03T09:48:54.402248Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1912.01811","last_updated":"2019-12-04T06:04:03Z","snapshot_observed_at":"2026-07-06T08:41:55.255378Z","submitted_at":"2019-12-04T06:04:03Z","title":"Drone-based Joint Density Map Estimation, Localization and Tracking with Space-Time Multi-Scale Attention Network","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1912.01811","snapshot_observed_at":"2026-08-03T09:48:54.509683Z","title":"Drone- based joint density map estimation, localization and tracking with space- time multi-scale attention network,","venue":null,"work_id":null,"year":1912},"citing_paper":{"arxiv_id":"2601.12500","last_updated":"2026-05-28T09:52:35Z","snapshot_observed_at":"2026-08-07T11:18:00.769993Z","submitted_at":"2026-01-18T17:17:31Z","title":"Video Individual Counting and Tracking from Moving Drones: A Benchmark and Methods","version":2},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-08-03T09:48:54.509683Z"},"links":{"cited_paper":"/paper/1912.01811","citing_paper":"/paper/2601.12500"},"observation_digest":"sha256:ffba31aec9f669717cf96fc5c198918312e870330710f21870d1e69d2ae68ace","observation_id":"a99990e7-ae05-432d-be41-044c563b9b5c","resolution":{"observed_at":"2026-08-03T09:48:54.509683Z","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":"2026-08-03T09:48:54.648437Z","title":"A large- scale drone based thermal infrared benchmark and inception transformer network for crowd counting,","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2601.12500","last_updated":"2026-05-28T09:52:35Z","snapshot_observed_at":"2026-08-07T11:18:00.769993Z","submitted_at":"2026-01-18T17:17:31Z","title":"Video Individual Counting and Tracking from Moving Drones: A Benchmark and Methods","version":2},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-08-03T09:48:54.648437Z"},"links":{"citing_paper":"/paper/2601.12500"},"observation_digest":"sha256:61427ba2294b347c7634790a3caa19bea4fff15d5a47528047fe516f1e903c73","observation_id":"bd4b8396-a1e0-443c-95dc-d202e5e95ccf","resolution":{"observed_at":"2026-08-03T09:48:54.648437Z","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":"2026-08-03T09:48:54.808729Z","title":"Enhanced uav-dot for uav crowd localization: Adaptive gaussian heat map and attention mechanism to address scale/low-light challenges,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2601.12500","last_updated":"2026-05-28T09:52:35Z","snapshot_observed_at":"2026-08-07T11:18:00.769993Z","submitted_at":"2026-01-18T17:17:31Z","title":"Video Individual Counting and Tracking from Moving Drones: A Benchmark and Methods","version":2},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-08-03T09:48:54.808729Z"},"links":{"citing_paper":"/paper/2601.12500"},"observation_digest":"sha256:0400556b94f7a1e4ef13e761250e29fa6e4c75bf8d1b6bfa841cecbfeae9bab0","observation_id":"2997807d-85af-42e4-aecc-23302102f101","resolution":{"observed_at":"2026-08-03T09:48:54.808729Z","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":"2026-08-03T09:48:54.977887Z","title":"Drone-person tracking in uniform appearance crowd: A new dataset,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2601.12500","last_updated":"2026-05-28T09:52:35Z","snapshot_observed_at":"2026-08-07T11:18:00.769993Z","submitted_at":"2026-01-18T17:17:31Z","title":"Video Individual Counting and Tracking from Moving Drones: A Benchmark and Methods","version":2},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-08-03T09:48:54.977887Z"},"links":{"citing_paper":"/paper/2601.12500"},"observation_digest":"sha256:729f74a4d796d2a1066cb5d8a5d082493e5b32db837e2b37c04e82e5efad161c","observation_id":"277838fd-84ce-4031-8530-cbd425ec04e7","resolution":{"observed_at":"2026-08-03T09:48:54.977887Z","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":"2026-08-03T09:48:55.160703Z","title":"Dense- track: Drone-based crowd tracking via density-aware motion-appearance IEEE TRANSACTIONS 16 synergy,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2601.12500","last_updated":"2026-05-28T09:52:35Z","snapshot_observed_at":"2026-08-07T11:18:00.769993Z","submitted_at":"2026-01-18T17:17:31Z","title":"Video Individual Counting and Tracking from Moving Drones: A Benchmark and Methods","version":2},"reference_index":73,"source":"pdf_text","source_observed_at":"2026-08-03T09:48:55.160703Z"},"links":{"citing_paper":"/paper/2601.12500"},"observation_digest":"sha256:86d849a59c882b65d6ec64cc15be764da9d052d34e5601c736ed2846f4e587ec","observation_id":"0e92f6dd-c2e9-460c-bb65-dbac023951c7","resolution":{"observed_at":"2026-08-03T09:48:55.160703Z","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":"2026-08-03T09:48:55.310330Z","title":"Multi-frame attention with feature-level warping for drone crowd tracking,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2601.12500","last_updated":"2026-05-28T09:52:35Z","snapshot_observed_at":"2026-08-07T11:18:00.769993Z","submitted_at":"2026-01-18T17:17:31Z","title":"Video Individual Counting and Tracking from Moving Drones: A Benchmark and Methods","version":2},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-08-03T09:48:55.310330Z"},"links":{"citing_paper":"/paper/2601.12500"},"observation_digest":"sha256:d1f71710c2f553d32940c1a28fa25947d0acdd8db818bb8a812c97f05f37cdac","observation_id":"c22eda67-484b-4bb9-8b25-73e9a46e4041","resolution":{"observed_at":"2026-08-03T09:48:55.310330Z","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":"2026-08-03T09:48:55.453285Z","title":"Tracking pedestrian heads in dense crowd,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2601.12500","last_updated":"2026-05-28T09:52:35Z","snapshot_observed_at":"2026-08-07T11:18:00.769993Z","submitted_at":"2026-01-18T17:17:31Z","title":"Video Individual Counting and Tracking from Moving Drones: A Benchmark and Methods","version":2},"reference_index":75,"source":"pdf_text","source_observed_at":"2026-08-03T09:48:55.453285Z"},"links":{"citing_paper":"/paper/2601.12500"},"observation_digest":"sha256:3f16663a1825f2321cd07240450a39fd2e2da64c17794c57b81852544584b9d7","observation_id":"ceb7bb6f-1080-4f9b-adb5-f46fc607bd17","resolution":{"observed_at":"2026-08-03T09:48:55.453285Z","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":"2026-08-03T09:48:55.596733Z","title":"Superglue: Learning feature matching with graph neural networks,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2601.12500","last_updated":"2026-05-28T09:52:35Z","snapshot_observed_at":"2026-08-07T11:18:00.769993Z","submitted_at":"2026-01-18T17:17:31Z","title":"Video Individual Counting and Tracking from Moving Drones: A Benchmark and Methods","version":2},"reference_index":76,"source":"pdf_text","source_observed_at":"2026-08-03T09:48:55.596733Z"},"links":{"citing_paper":"/paper/2601.12500"},"observation_digest":"sha256:ee1aec0a23458bf756a9f03389994dbd2af76009b80660c10eba9245b8f80ad1","observation_id":"9585d986-f6b1-47d4-9ada-4c652ff72341","resolution":{"observed_at":"2026-08-03T09:48:55.596733Z","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":"2026-08-03T09:48:55.712759Z","title":"Sinkhorn distances: Lightspeed computation of optimal transport,","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2601.12500","last_updated":"2026-05-28T09:52:35Z","snapshot_observed_at":"2026-08-07T11:18:00.769993Z","submitted_at":"2026-01-18T17:17:31Z","title":"Video Individual Counting and Tracking from Moving Drones: A Benchmark and Methods","version":2},"reference_index":77,"source":"pdf_text","source_observed_at":"2026-08-03T09:48:55.712759Z"},"links":{"citing_paper":"/paper/2601.12500"},"observation_digest":"sha256:baf37e3e3d3fc9b2976c1fdd85e18f78587f8334a9d9ed4286f7924ffb1ae374","observation_id":"f7ef36f1-eb4d-431a-80ac-f681ad1b2977","resolution":{"observed_at":"2026-08-03T09:48:55.712759Z","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":"2026-08-03T09:48:55.884219Z","title":"Algorithms for the assignment and transportation prob- lems,","venue":null,"work_id":null,"year":1957},"citing_paper":{"arxiv_id":"2601.12500","last_updated":"2026-05-28T09:52:35Z","snapshot_observed_at":"2026-08-07T11:18:00.769993Z","submitted_at":"2026-01-18T17:17:31Z","title":"Video Individual Counting and Tracking from Moving Drones: A Benchmark and Methods","version":2},"reference_index":78,"source":"pdf_text","source_observed_at":"2026-08-03T09:48:55.884219Z"},"links":{"citing_paper":"/paper/2601.12500"},"observation_digest":"sha256:ed14a7e20fcdcdc987f1f694e95cb9fb8b52d44d3710fda1a6b98645d39cda3e","observation_id":"42e574bb-d480-44a9-ac64-2c4e941dac4b","resolution":{"observed_at":"2026-08-03T09:48:55.884219Z","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":"2026-08-03T09:48:56.078582Z","title":"Hota: A higher order metric for evaluating multi-object tracking,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2601.12500","last_updated":"2026-05-28T09:52:35Z","snapshot_observed_at":"2026-08-07T11:18:00.769993Z","submitted_at":"2026-01-18T17:17:31Z","title":"Video Individual Counting and Tracking from Moving Drones: A Benchmark and Methods","version":2},"reference_index":79,"source":"pdf_text","source_observed_at":"2026-08-03T09:48:56.078582Z"},"links":{"citing_paper":"/paper/2601.12500"},"observation_digest":"sha256:bcfde71f529da78eeb84a7886197aa3d496935da8dee3fddc92af54b3855718e","observation_id":"cea25290-69eb-4690-9c0e-92485e5ae6ff","resolution":{"observed_at":"2026-08-03T09:48:56.078582Z","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":"2026-08-03T09:48:56.165439Z","title":"Evaluating multiple object tracking performance: the clear mot metrics,","venue":null,"work_id":null,"year":2008},"citing_paper":{"arxiv_id":"2601.12500","last_updated":"2026-05-28T09:52:35Z","snapshot_observed_at":"2026-08-07T11:18:00.769993Z","submitted_at":"2026-01-18T17:17:31Z","title":"Video Individual Counting and Tracking from Moving Drones: A Benchmark and Methods","version":2},"reference_index":80,"source":"pdf_text","source_observed_at":"2026-08-03T09:48:56.165439Z"},"links":{"citing_paper":"/paper/2601.12500"},"observation_digest":"sha256:59d552253c0039d9f9b60d898dd4984b029cdece3dc5056730a2a7b6d17abf34","observation_id":"50b8cde0-78b2-4336-8e0e-65511f9edca2","resolution":{"observed_at":"2026-08-03T09:48:56.165439Z","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":"2026-08-03T09:48:56.261394Z","title":"Perfor- mance measures and a data set for multi-target, multi-camera tracking,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2601.12500","last_updated":"2026-05-28T09:52:35Z","snapshot_observed_at":"2026-08-07T11:18:00.769993Z","submitted_at":"2026-01-18T17:17:31Z","title":"Video Individual Counting and Tracking from Moving Drones: A Benchmark and Methods","version":2},"reference_index":81,"source":"pdf_text","source_observed_at":"2026-08-03T09:48:56.261394Z"},"links":{"citing_paper":"/paper/2601.12500"},"observation_digest":"sha256:34ed1890f581acd1321ce6aebd4bbaafdf877c306e2e082091ca3c20767ac1e6","observation_id":"ec8edf06-9e1f-4a8f-b97d-c61a28945b61","resolution":{"observed_at":"2026-08-03T09:48:56.261394Z","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":"2026-08-03T09:48:56.407903Z","title":"Deep residual learning for image recognition,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2601.12500","last_updated":"2026-05-28T09:52:35Z","snapshot_observed_at":"2026-08-07T11:18:00.769993Z","submitted_at":"2026-01-18T17:17:31Z","title":"Video Individual Counting and Tracking from Moving Drones: A Benchmark and Methods","version":2},"reference_index":82,"source":"pdf_text","source_observed_at":"2026-08-03T09:48:56.407903Z"},"links":{"citing_paper":"/paper/2601.12500"},"observation_digest":"sha256:bd254b13f903b49693e31e86eb981b4b311ba037a388706350e886c816afc2ac","observation_id":"de63b1ca-718e-43fd-8fc1-3c8a6a055aef","resolution":{"observed_at":"2026-08-03T09:48:56.407903Z","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":"2026-08-03T09:48:56.540106Z","title":"Feature pyramid networks for object detection,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2601.12500","last_updated":"2026-05-28T09:52:35Z","snapshot_observed_at":"2026-08-07T11:18:00.769993Z","submitted_at":"2026-01-18T17:17:31Z","title":"Video Individual Counting and Tracking from Moving Drones: A Benchmark and Methods","version":2},"reference_index":83,"source":"pdf_text","source_observed_at":"2026-08-03T09:48:56.540106Z"},"links":{"citing_paper":"/paper/2601.12500"},"observation_digest":"sha256:fc807de2630e024692c49f1bcfeebb53d20a38d28ed576af61b9ea59afca31fa","observation_id":"1ca90db4-74d2-493b-8c5d-f33fff5cc3f4","resolution":{"observed_at":"2026-08-03T09:48:56.540106Z","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":"2026-08-03T09:48:56.732951Z","title":"Crossing-line crowd counting with two-phase deep neural networks,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2601.12500","last_updated":"2026-05-28T09:52:35Z","snapshot_observed_at":"2026-08-07T11:18:00.769993Z","submitted_at":"2026-01-18T17:17:31Z","title":"Video Individual Counting and Tracking from Moving Drones: A Benchmark and Methods","version":2},"reference_index":84,"source":"pdf_text","source_observed_at":"2026-08-03T09:48:56.732951Z"},"links":{"citing_paper":"/paper/2601.12500"},"observation_digest":"sha256:fbc7da37915cf181db57cd332a14dc22a7ef412083c29531ed5291986428b5bc","observation_id":"278036fe-d06c-4ae8-9e3e-b30385468b01","resolution":{"observed_at":"2026-08-03T09:48:56.732951Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2601.12500","last_updated":"2026-05-28T09:52:35Z","latest_version":2,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-07T11:18:00.769993Z","submitted_at":"2026-01-18T17:17:31Z","title":"Video Individual Counting and Tracking from Moving Drones: A Benchmark and Methods"},"reference_resolution":{"displayed":84,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":84,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":84},"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":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 84 of 84 outbound references and 0 inbound Pith citation observations for arXiv:2601.12500."}