{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:OLA2PBSQCMWFQHXY5VYQI5SYCT","short_pith_number":"pith:OLA2PBSQ","schema_version":"1.0","canonical_sha256":"72c1a78650132c581ef8ed7104765814e0c2619b83fba1c7881fec90a59f93b1","source":{"kind":"arxiv","id":"2503.10616","version":3},"attestation_state":"computed","paper":{"title":"OVTR: End-to-End Open-Vocabulary Multiple Object Tracking with Transformer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"En Yu, Jinyang Li, Sijia Chen, Wenbing Tao","submitted_at":"2025-03-13T17:56:10Z","abstract_excerpt":"Open-vocabulary multiple object tracking aims to generalize trackers to unseen categories during training, enabling their application across a variety of real-world scenarios. However, the existing open-vocabulary tracker is constrained by its framework structure, isolated frame-level perception, and insufficient modal interactions, which hinder its performance in open-vocabulary classification and tracking. In this paper, we propose OVTR (End-to-End Open-Vocabulary Multiple Object Tracking with TRansformer), the first end-to-end open-vocabulary tracker that models motion, appearance, and cate"},"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":"2503.10616","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-13T17:56:10Z","cross_cats_sorted":[],"title_canon_sha256":"94ac98ca6d9d58938c8c8715e3f615a8e4fca34a5d096c27a4bb0a3303abaee1","abstract_canon_sha256":"7e040144e7a0123aded77ab6bba1a8d3fc75d426f2fe0a6db43db55195bbab4c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:41:21.544831Z","signature_b64":"QDerd7yx2+kwYNum9SmHLD6jP5/+iZROFoNYl5PfjWMn64FJvjxYJyU9sc1qrotSGXJp9/e20WFvBR0KJQCIAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"72c1a78650132c581ef8ed7104765814e0c2619b83fba1c7881fec90a59f93b1","last_reissued_at":"2026-07-05T10:41:21.544305Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:41:21.544305Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OVTR: End-to-End Open-Vocabulary Multiple Object Tracking with Transformer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"En Yu, Jinyang Li, Sijia Chen, Wenbing Tao","submitted_at":"2025-03-13T17:56:10Z","abstract_excerpt":"Open-vocabulary multiple object tracking aims to generalize trackers to unseen categories during training, enabling their application across a variety of real-world scenarios. However, the existing open-vocabulary tracker is constrained by its framework structure, isolated frame-level perception, and insufficient modal interactions, which hinder its performance in open-vocabulary classification and tracking. In this paper, we propose OVTR (End-to-End Open-Vocabulary Multiple Object Tracking with TRansformer), the first end-to-end open-vocabulary tracker that models motion, appearance, and cate"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.10616","kind":"arxiv","version":3},"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/2503.10616/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":"2503.10616","created_at":"2026-07-05T10:41:21.544375+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.10616v3","created_at":"2026-07-05T10:41:21.544375+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.10616","created_at":"2026-07-05T10:41:21.544375+00:00"},{"alias_kind":"pith_short_12","alias_value":"OLA2PBSQCMWF","created_at":"2026-07-05T10:41:21.544375+00:00"},{"alias_kind":"pith_short_16","alias_value":"OLA2PBSQCMWFQHXY","created_at":"2026-07-05T10:41:21.544375+00:00"},{"alias_kind":"pith_short_8","alias_value":"OLA2PBSQ","created_at":"2026-07-05T10:41:21.544375+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.00503","citing_title":"PET-DINO: Unifying Visual Cues into Grounding DINO with Prompt-Enriched Training","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OLA2PBSQCMWFQHXY5VYQI5SYCT","json":"https://pith.science/pith/OLA2PBSQCMWFQHXY5VYQI5SYCT.json","graph_json":"https://pith.science/api/pith-number/OLA2PBSQCMWFQHXY5VYQI5SYCT/graph.json","events_json":"https://pith.science/api/pith-number/OLA2PBSQCMWFQHXY5VYQI5SYCT/events.json","paper":"https://pith.science/paper/OLA2PBSQ"},"agent_actions":{"view_html":"https://pith.science/pith/OLA2PBSQCMWFQHXY5VYQI5SYCT","download_json":"https://pith.science/pith/OLA2PBSQCMWFQHXY5VYQI5SYCT.json","view_paper":"https://pith.science/paper/OLA2PBSQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.10616&json=true","fetch_graph":"https://pith.science/api/pith-number/OLA2PBSQCMWFQHXY5VYQI5SYCT/graph.json","fetch_events":"https://pith.science/api/pith-number/OLA2PBSQCMWFQHXY5VYQI5SYCT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OLA2PBSQCMWFQHXY5VYQI5SYCT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OLA2PBSQCMWFQHXY5VYQI5SYCT/action/storage_attestation","attest_author":"https://pith.science/pith/OLA2PBSQCMWFQHXY5VYQI5SYCT/action/author_attestation","sign_citation":"https://pith.science/pith/OLA2PBSQCMWFQHXY5VYQI5SYCT/action/citation_signature","submit_replication":"https://pith.science/pith/OLA2PBSQCMWFQHXY5VYQI5SYCT/action/replication_record"}},"created_at":"2026-07-05T10:41:21.544375+00:00","updated_at":"2026-07-05T10:41:21.544375+00:00"}