{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:YDXFKJBA5EZSJXWK3XL73LUKGC","short_pith_number":"pith:YDXFKJBA","schema_version":"1.0","canonical_sha256":"c0ee552420e93324decaddd7fdae8a30a16acc8b9417b6076533aee51a875c04","source":{"kind":"arxiv","id":"2205.15495","version":1},"attestation_state":"computed","paper":{"title":"Joint Spatial-Temporal and Appearance Modeling with Transformer for Multiple Object Tracking","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Changshui Zhang, Peng Dai, Renliang Weng, Yiqiang Feng","submitted_at":"2022-05-31T01:19:18Z","abstract_excerpt":"The recent trend in multiple object tracking (MOT) is heading towards leveraging deep learning to boost the tracking performance. In this paper, we propose a novel solution named TransSTAM, which leverages Transformer to effectively model both the appearance features of each object and the spatial-temporal relationships among objects. TransSTAM consists of two major parts: (1) The encoder utilizes the powerful self-attention mechanism of Transformer to learn discriminative features for each tracklet; (2) The decoder adopts the standard cross-attention mechanism to model the affinities between "},"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":"2205.15495","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-05-31T01:19:18Z","cross_cats_sorted":[],"title_canon_sha256":"9719297a30b129090079e2aca1e03012c6810878b845025d669ea05a14725dd3","abstract_canon_sha256":"df81d45c886ab581da7edc31308c2834e3d9d9d25978ce1d0001d4798f79d062"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:27:33.428970Z","signature_b64":"doGEQ5HuaBogP+4se4I+Pw0oVADFJbdvV2R2ulKFAn2ujaroUgOwNBCVF1ZcRi1sEY8ZyBmOiv22RpPtDxNmAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c0ee552420e93324decaddd7fdae8a30a16acc8b9417b6076533aee51a875c04","last_reissued_at":"2026-07-05T04:27:33.428378Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:27:33.428378Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Joint Spatial-Temporal and Appearance Modeling with Transformer for Multiple Object Tracking","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Changshui Zhang, Peng Dai, Renliang Weng, Yiqiang Feng","submitted_at":"2022-05-31T01:19:18Z","abstract_excerpt":"The recent trend in multiple object tracking (MOT) is heading towards leveraging deep learning to boost the tracking performance. In this paper, we propose a novel solution named TransSTAM, which leverages Transformer to effectively model both the appearance features of each object and the spatial-temporal relationships among objects. TransSTAM consists of two major parts: (1) The encoder utilizes the powerful self-attention mechanism of Transformer to learn discriminative features for each tracklet; (2) The decoder adopts the standard cross-attention mechanism to model the affinities between "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.15495","kind":"arxiv","version":1},"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/2205.15495/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":"2205.15495","created_at":"2026-07-05T04:27:33.428458+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.15495v1","created_at":"2026-07-05T04:27:33.428458+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.15495","created_at":"2026-07-05T04:27:33.428458+00:00"},{"alias_kind":"pith_short_12","alias_value":"YDXFKJBA5EZS","created_at":"2026-07-05T04:27:33.428458+00:00"},{"alias_kind":"pith_short_16","alias_value":"YDXFKJBA5EZSJXWK","created_at":"2026-07-05T04:27:33.428458+00:00"},{"alias_kind":"pith_short_8","alias_value":"YDXFKJBA","created_at":"2026-07-05T04:27:33.428458+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.01257","citing_title":"CAMELTrack: Context-Aware Multi-cue ExpLoitation for Online Multi-Object Tracking","ref_index":19,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YDXFKJBA5EZSJXWK3XL73LUKGC","json":"https://pith.science/pith/YDXFKJBA5EZSJXWK3XL73LUKGC.json","graph_json":"https://pith.science/api/pith-number/YDXFKJBA5EZSJXWK3XL73LUKGC/graph.json","events_json":"https://pith.science/api/pith-number/YDXFKJBA5EZSJXWK3XL73LUKGC/events.json","paper":"https://pith.science/paper/YDXFKJBA"},"agent_actions":{"view_html":"https://pith.science/pith/YDXFKJBA5EZSJXWK3XL73LUKGC","download_json":"https://pith.science/pith/YDXFKJBA5EZSJXWK3XL73LUKGC.json","view_paper":"https://pith.science/paper/YDXFKJBA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.15495&json=true","fetch_graph":"https://pith.science/api/pith-number/YDXFKJBA5EZSJXWK3XL73LUKGC/graph.json","fetch_events":"https://pith.science/api/pith-number/YDXFKJBA5EZSJXWK3XL73LUKGC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YDXFKJBA5EZSJXWK3XL73LUKGC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YDXFKJBA5EZSJXWK3XL73LUKGC/action/storage_attestation","attest_author":"https://pith.science/pith/YDXFKJBA5EZSJXWK3XL73LUKGC/action/author_attestation","sign_citation":"https://pith.science/pith/YDXFKJBA5EZSJXWK3XL73LUKGC/action/citation_signature","submit_replication":"https://pith.science/pith/YDXFKJBA5EZSJXWK3XL73LUKGC/action/replication_record"}},"created_at":"2026-07-05T04:27:33.428458+00:00","updated_at":"2026-07-05T04:27:33.428458+00:00"}