{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:U3ENRIKBPCUHUIMI2QZ4PPVARH","short_pith_number":"pith:U3ENRIKB","schema_version":"1.0","canonical_sha256":"a6c8d8a14178a87a2188d433c7bea089e201d367016d19f8459964e570b5f2a9","source":{"kind":"arxiv","id":"2206.04656","version":7},"attestation_state":"computed","paper":{"title":"Simple Cues Lead to a Strong Multi-Object Tracker","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guillem Bras\\'o, Ismail Elezi, Jenny Seidenschwarz, Laura Leal-Taix\\'e, Victor Castro Serrano","submitted_at":"2022-06-09T17:55:51Z","abstract_excerpt":"For a long time, the most common paradigm in Multi-Object Tracking was tracking-by-detection (TbD), where objects are first detected and then associated over video frames. For association, most models resourced to motion and appearance cues, e.g., re-identification networks. Recent approaches based on attention propose to learn the cues in a data-driven manner, showing impressive results. In this paper, we ask ourselves whether simple good old TbD methods are also capable of achieving the performance of end-to-end models. To this end, we propose two key ingredients that allow a standard re-ide"},"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":"2206.04656","kind":"arxiv","version":7},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-06-09T17:55:51Z","cross_cats_sorted":[],"title_canon_sha256":"f1b9ff8b69b8eff4cebc339c08f597dce320a7bfaf7b13baeb8a781d0ebd4847","abstract_canon_sha256":"c1842484e088bfee88a47d42cd7d267764e9fa4af44b4978efca10d8359eaad9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:04:33.894500Z","signature_b64":"X8Bg9Wcyl6GJ6TLlKzqaltseAdbJ2VGzKdHljB0rgxywNF5e4kW/mtXRfA3ycBk4rbGZmApdiU0k8Jd6tgwzBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a6c8d8a14178a87a2188d433c7bea089e201d367016d19f8459964e570b5f2a9","last_reissued_at":"2026-07-05T06:04:33.894061Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:04:33.894061Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Simple Cues Lead to a Strong Multi-Object Tracker","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guillem Bras\\'o, Ismail Elezi, Jenny Seidenschwarz, Laura Leal-Taix\\'e, Victor Castro Serrano","submitted_at":"2022-06-09T17:55:51Z","abstract_excerpt":"For a long time, the most common paradigm in Multi-Object Tracking was tracking-by-detection (TbD), where objects are first detected and then associated over video frames. For association, most models resourced to motion and appearance cues, e.g., re-identification networks. Recent approaches based on attention propose to learn the cues in a data-driven manner, showing impressive results. In this paper, we ask ourselves whether simple good old TbD methods are also capable of achieving the performance of end-to-end models. To this end, we propose two key ingredients that allow a standard re-ide"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.04656","kind":"arxiv","version":7},"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/2206.04656/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":"2206.04656","created_at":"2026-07-05T06:04:33.894114+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.04656v7","created_at":"2026-07-05T06:04:33.894114+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.04656","created_at":"2026-07-05T06:04:33.894114+00:00"},{"alias_kind":"pith_short_12","alias_value":"U3ENRIKBPCUH","created_at":"2026-07-05T06:04:33.894114+00:00"},{"alias_kind":"pith_short_16","alias_value":"U3ENRIKBPCUHUIMI","created_at":"2026-07-05T06:04:33.894114+00:00"},{"alias_kind":"pith_short_8","alias_value":"U3ENRIKB","created_at":"2026-07-05T06:04:33.894114+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2509.02111","citing_title":"NOOUGAT: Towards Unified Online and Offline Multi-Object Tracking","ref_index":38,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/U3ENRIKBPCUHUIMI2QZ4PPVARH","json":"https://pith.science/pith/U3ENRIKBPCUHUIMI2QZ4PPVARH.json","graph_json":"https://pith.science/api/pith-number/U3ENRIKBPCUHUIMI2QZ4PPVARH/graph.json","events_json":"https://pith.science/api/pith-number/U3ENRIKBPCUHUIMI2QZ4PPVARH/events.json","paper":"https://pith.science/paper/U3ENRIKB"},"agent_actions":{"view_html":"https://pith.science/pith/U3ENRIKBPCUHUIMI2QZ4PPVARH","download_json":"https://pith.science/pith/U3ENRIKBPCUHUIMI2QZ4PPVARH.json","view_paper":"https://pith.science/paper/U3ENRIKB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.04656&json=true","fetch_graph":"https://pith.science/api/pith-number/U3ENRIKBPCUHUIMI2QZ4PPVARH/graph.json","fetch_events":"https://pith.science/api/pith-number/U3ENRIKBPCUHUIMI2QZ4PPVARH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U3ENRIKBPCUHUIMI2QZ4PPVARH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U3ENRIKBPCUHUIMI2QZ4PPVARH/action/storage_attestation","attest_author":"https://pith.science/pith/U3ENRIKBPCUHUIMI2QZ4PPVARH/action/author_attestation","sign_citation":"https://pith.science/pith/U3ENRIKBPCUHUIMI2QZ4PPVARH/action/citation_signature","submit_replication":"https://pith.science/pith/U3ENRIKBPCUHUIMI2QZ4PPVARH/action/replication_record"}},"created_at":"2026-07-05T06:04:33.894114+00:00","updated_at":"2026-07-05T06:04:33.894114+00:00"}