{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:TU3JLTYNP7U45IEUHAMOYF7X6X","short_pith_number":"pith:TU3JLTYN","schema_version":"1.0","canonical_sha256":"9d3695cf0d7fe9cea0943818ec17f7f5cebb7a64db2a0f4e5755bf2c09d94afa","source":{"kind":"arxiv","id":"2102.02267","version":2},"attestation_state":"computed","paper":{"title":"DEFT: Detection Embeddings for Tracking","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"J. Ross Beveridge, Mohamed Chaabane, Peter Zhang, Stephen O'Hara","submitted_at":"2021-02-03T20:00:44Z","abstract_excerpt":"Most modern multiple object tracking (MOT) systems follow the tracking-by-detection paradigm, consisting of a detector followed by a method for associating detections into tracks. There is a long history in tracking of combining motion and appearance features to provide robustness to occlusions and other challenges, but typically this comes with the trade-off of a more complex and slower implementation. Recent successes on popular 2D tracking benchmarks indicate that top-scores can be achieved using a state-of-the-art detector and relatively simple associations relying on single-frame spatial "},"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":"2102.02267","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-02-03T20:00:44Z","cross_cats_sorted":[],"title_canon_sha256":"e0aab622e336710561f72eca50b1275dcfbebe6f6d1d642e2512e0a4d9e093b4","abstract_canon_sha256":"a10bf80863581aa560075578f27976007a01c635150913bf3275548bba5c9094"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:46:44.136552Z","signature_b64":"3GQiDIu+bqhmETl8oe8kDkO/PFxdNCyyqwI8GCO/7UYw3hDbK4RDm1v9YRL5zu0WwcBYNU5LAVvDqHZyEI7tBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9d3695cf0d7fe9cea0943818ec17f7f5cebb7a64db2a0f4e5755bf2c09d94afa","last_reissued_at":"2026-07-05T02:46:44.136070Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:46:44.136070Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DEFT: Detection Embeddings for Tracking","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"J. Ross Beveridge, Mohamed Chaabane, Peter Zhang, Stephen O'Hara","submitted_at":"2021-02-03T20:00:44Z","abstract_excerpt":"Most modern multiple object tracking (MOT) systems follow the tracking-by-detection paradigm, consisting of a detector followed by a method for associating detections into tracks. There is a long history in tracking of combining motion and appearance features to provide robustness to occlusions and other challenges, but typically this comes with the trade-off of a more complex and slower implementation. Recent successes on popular 2D tracking benchmarks indicate that top-scores can be achieved using a state-of-the-art detector and relatively simple associations relying on single-frame spatial "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.02267","kind":"arxiv","version":2},"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/2102.02267/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":"2102.02267","created_at":"2026-07-05T02:46:44.136126+00:00"},{"alias_kind":"arxiv_version","alias_value":"2102.02267v2","created_at":"2026-07-05T02:46:44.136126+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.02267","created_at":"2026-07-05T02:46:44.136126+00:00"},{"alias_kind":"pith_short_12","alias_value":"TU3JLTYNP7U4","created_at":"2026-07-05T02:46:44.136126+00:00"},{"alias_kind":"pith_short_16","alias_value":"TU3JLTYNP7U45IEU","created_at":"2026-07-05T02:46:44.136126+00:00"},{"alias_kind":"pith_short_8","alias_value":"TU3JLTYN","created_at":"2026-07-05T02:46:44.136126+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2603.19929","citing_title":"RAM: Recover Any 3D Human Motion in-the-Wild","ref_index":9,"is_internal_anchor":false},{"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":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TU3JLTYNP7U45IEUHAMOYF7X6X","json":"https://pith.science/pith/TU3JLTYNP7U45IEUHAMOYF7X6X.json","graph_json":"https://pith.science/api/pith-number/TU3JLTYNP7U45IEUHAMOYF7X6X/graph.json","events_json":"https://pith.science/api/pith-number/TU3JLTYNP7U45IEUHAMOYF7X6X/events.json","paper":"https://pith.science/paper/TU3JLTYN"},"agent_actions":{"view_html":"https://pith.science/pith/TU3JLTYNP7U45IEUHAMOYF7X6X","download_json":"https://pith.science/pith/TU3JLTYNP7U45IEUHAMOYF7X6X.json","view_paper":"https://pith.science/paper/TU3JLTYN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2102.02267&json=true","fetch_graph":"https://pith.science/api/pith-number/TU3JLTYNP7U45IEUHAMOYF7X6X/graph.json","fetch_events":"https://pith.science/api/pith-number/TU3JLTYNP7U45IEUHAMOYF7X6X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TU3JLTYNP7U45IEUHAMOYF7X6X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TU3JLTYNP7U45IEUHAMOYF7X6X/action/storage_attestation","attest_author":"https://pith.science/pith/TU3JLTYNP7U45IEUHAMOYF7X6X/action/author_attestation","sign_citation":"https://pith.science/pith/TU3JLTYNP7U45IEUHAMOYF7X6X/action/citation_signature","submit_replication":"https://pith.science/pith/TU3JLTYNP7U45IEUHAMOYF7X6X/action/replication_record"}},"created_at":"2026-07-05T02:46:44.136126+00:00","updated_at":"2026-07-05T02:46:44.136126+00:00"}