{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:LDOAE4QBSDUZ7ZKHY4S4W64CJL","short_pith_number":"pith:LDOAE4QB","schema_version":"1.0","canonical_sha256":"58dc02720190e99fe547c725cb7b824adecc89532fc7b4fc3dbd9908064019e0","source":{"kind":"arxiv","id":"2004.01888","version":6},"attestation_state":"computed","paper":{"title":"FairMOT: On the Fairness of Detection and Re-Identification in Multiple Object Tracking","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chunyu Wang, Wenjun Zeng, Wenyu Liu, Xinggang Wang, Yifu Zhang","submitted_at":"2020-04-04T08:18:00Z","abstract_excerpt":"Multi-object tracking (MOT) is an important problem in computer vision which has a wide range of applications. Formulating MOT as multi-task learning of object detection and re-ID in a single network is appealing since it allows joint optimization of the two tasks and enjoys high computation efficiency. However, we find that the two tasks tend to compete with each other which need to be carefully addressed. In particular, previous works usually treat re-ID as a secondary task whose accuracy is heavily affected by the primary detection task. As a result, the network is biased to the primary det"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2004.01888","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-04-04T08:18:00Z","cross_cats_sorted":[],"title_canon_sha256":"2f13fdceaea345652569ef1c7b081103f76dd1d6a679d5fd9d53cb1a63ec073e","abstract_canon_sha256":"704eb7f2f3a1edf6240f6e66fe14da39938a1cbb97eda5c5c5fbebeb75cf6611"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:23:36.365436Z","signature_b64":"ExHEx2/cb4MEGF6PDAg0fiFovKzUzOliIFh48/SsoI21w9v40y8/GyHJrn4X/D43me6aSfYzhaSQgUfyr9hqAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"58dc02720190e99fe547c725cb7b824adecc89532fc7b4fc3dbd9908064019e0","last_reissued_at":"2026-07-05T03:23:36.364913Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:23:36.364913Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FairMOT: On the Fairness of Detection and Re-Identification in Multiple Object Tracking","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chunyu Wang, Wenjun Zeng, Wenyu Liu, Xinggang Wang, Yifu Zhang","submitted_at":"2020-04-04T08:18:00Z","abstract_excerpt":"Multi-object tracking (MOT) is an important problem in computer vision which has a wide range of applications. Formulating MOT as multi-task learning of object detection and re-ID in a single network is appealing since it allows joint optimization of the two tasks and enjoys high computation efficiency. However, we find that the two tasks tend to compete with each other which need to be carefully addressed. In particular, previous works usually treat re-ID as a secondary task whose accuracy is heavily affected by the primary detection task. As a result, the network is biased to the primary det"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.01888","kind":"arxiv","version":6},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2004.01888/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2004.01888","created_at":"2026-07-05T03:23:36.364971+00:00"},{"alias_kind":"arxiv_version","alias_value":"2004.01888v6","created_at":"2026-07-05T03:23:36.364971+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.01888","created_at":"2026-07-05T03:23:36.364971+00:00"},{"alias_kind":"pith_short_12","alias_value":"LDOAE4QBSDUZ","created_at":"2026-07-05T03:23:36.364971+00:00"},{"alias_kind":"pith_short_16","alias_value":"LDOAE4QBSDUZ7ZKH","created_at":"2026-07-05T03:23:36.364971+00:00"},{"alias_kind":"pith_short_8","alias_value":"LDOAE4QB","created_at":"2026-07-05T03:23:36.364971+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.00362","citing_title":"Time-series Meets Complex Motion Modeling: Robust and Computational-effective Motion Predictor for Multi-object Tracking","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LDOAE4QBSDUZ7ZKHY4S4W64CJL","json":"https://pith.science/pith/LDOAE4QBSDUZ7ZKHY4S4W64CJL.json","graph_json":"https://pith.science/api/pith-number/LDOAE4QBSDUZ7ZKHY4S4W64CJL/graph.json","events_json":"https://pith.science/api/pith-number/LDOAE4QBSDUZ7ZKHY4S4W64CJL/events.json","paper":"https://pith.science/paper/LDOAE4QB"},"agent_actions":{"view_html":"https://pith.science/pith/LDOAE4QBSDUZ7ZKHY4S4W64CJL","download_json":"https://pith.science/pith/LDOAE4QBSDUZ7ZKHY4S4W64CJL.json","view_paper":"https://pith.science/paper/LDOAE4QB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2004.01888&json=true","fetch_graph":"https://pith.science/api/pith-number/LDOAE4QBSDUZ7ZKHY4S4W64CJL/graph.json","fetch_events":"https://pith.science/api/pith-number/LDOAE4QBSDUZ7ZKHY4S4W64CJL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LDOAE4QBSDUZ7ZKHY4S4W64CJL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LDOAE4QBSDUZ7ZKHY4S4W64CJL/action/storage_attestation","attest_author":"https://pith.science/pith/LDOAE4QBSDUZ7ZKHY4S4W64CJL/action/author_attestation","sign_citation":"https://pith.science/pith/LDOAE4QBSDUZ7ZKHY4S4W64CJL/action/citation_signature","submit_replication":"https://pith.science/pith/LDOAE4QBSDUZ7ZKHY4S4W64CJL/action/replication_record"}},"created_at":"2026-07-05T03:23:36.364971+00:00","updated_at":"2026-07-05T03:23:36.364971+00:00"}