{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:UXVRMGNGTJAUFRNOYBE3K3B754","short_pith_number":"pith:UXVRMGNG","schema_version":"1.0","canonical_sha256":"a5eb1619a69a4142c5aec049b56c3fef1b48088e508747945217520a1d7290db","source":{"kind":"arxiv","id":"2403.13042","version":1},"attestation_state":"computed","paper":{"title":"TAPTR: Tracking Any Point with Transformers as Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Feng Li, Hao Zhang, Hongyang Li, Lei Zhang, Shilong Liu, Tianhe Ren, Zhaoyang Zeng","submitted_at":"2024-03-19T17:57:09Z","abstract_excerpt":"In this paper, we propose a simple and strong framework for Tracking Any Point with TRansformers (TAPTR). Based on the observation that point tracking bears a great resemblance to object detection and tracking, we borrow designs from DETR-like algorithms to address the task of TAP. In the proposed framework, in each video frame, each tracking point is represented as a point query, which consists of a positional part and a content part. As in DETR, each query (its position and content feature) is naturally updated layer by layer. Its visibility is predicted by its updated content feature. Queri"},"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":"2403.13042","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-19T17:57:09Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"c36c51623e1aaf140e9ac000044b555d6a762ce062d59142285d27dd6e964383","abstract_canon_sha256":"3fb61cf610e228b7731e2090d9b1f065ef25af3234d85f915201b0978efa6c94"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:58:30.441013Z","signature_b64":"nID552B3qRjTfikYsCOvlmaGBbWDvGdCWFqcPpJ7HR4J+8Rh8nOzNVuxOl5bZ1UHVHS1vH0sLrFxzlU7xjliBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a5eb1619a69a4142c5aec049b56c3fef1b48088e508747945217520a1d7290db","last_reissued_at":"2026-07-05T07:58:30.440525Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:58:30.440525Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TAPTR: Tracking Any Point with Transformers as Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Feng Li, Hao Zhang, Hongyang Li, Lei Zhang, Shilong Liu, Tianhe Ren, Zhaoyang Zeng","submitted_at":"2024-03-19T17:57:09Z","abstract_excerpt":"In this paper, we propose a simple and strong framework for Tracking Any Point with TRansformers (TAPTR). Based on the observation that point tracking bears a great resemblance to object detection and tracking, we borrow designs from DETR-like algorithms to address the task of TAP. In the proposed framework, in each video frame, each tracking point is represented as a point query, which consists of a positional part and a content part. As in DETR, each query (its position and content feature) is naturally updated layer by layer. Its visibility is predicted by its updated content feature. Queri"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.13042","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/2403.13042/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":"2403.13042","created_at":"2026-07-05T07:58:30.440589+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.13042v1","created_at":"2026-07-05T07:58:30.440589+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.13042","created_at":"2026-07-05T07:58:30.440589+00:00"},{"alias_kind":"pith_short_12","alias_value":"UXVRMGNGTJAU","created_at":"2026-07-05T07:58:30.440589+00:00"},{"alias_kind":"pith_short_16","alias_value":"UXVRMGNGTJAUFRNO","created_at":"2026-07-05T07:58:30.440589+00:00"},{"alias_kind":"pith_short_8","alias_value":"UXVRMGNG","created_at":"2026-07-05T07:58:30.440589+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.12218","citing_title":"Exploring Temporally-Aware Features for Point Tracking","ref_index":31,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UXVRMGNGTJAUFRNOYBE3K3B754","json":"https://pith.science/pith/UXVRMGNGTJAUFRNOYBE3K3B754.json","graph_json":"https://pith.science/api/pith-number/UXVRMGNGTJAUFRNOYBE3K3B754/graph.json","events_json":"https://pith.science/api/pith-number/UXVRMGNGTJAUFRNOYBE3K3B754/events.json","paper":"https://pith.science/paper/UXVRMGNG"},"agent_actions":{"view_html":"https://pith.science/pith/UXVRMGNGTJAUFRNOYBE3K3B754","download_json":"https://pith.science/pith/UXVRMGNGTJAUFRNOYBE3K3B754.json","view_paper":"https://pith.science/paper/UXVRMGNG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.13042&json=true","fetch_graph":"https://pith.science/api/pith-number/UXVRMGNGTJAUFRNOYBE3K3B754/graph.json","fetch_events":"https://pith.science/api/pith-number/UXVRMGNGTJAUFRNOYBE3K3B754/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UXVRMGNGTJAUFRNOYBE3K3B754/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UXVRMGNGTJAUFRNOYBE3K3B754/action/storage_attestation","attest_author":"https://pith.science/pith/UXVRMGNGTJAUFRNOYBE3K3B754/action/author_attestation","sign_citation":"https://pith.science/pith/UXVRMGNGTJAUFRNOYBE3K3B754/action/citation_signature","submit_replication":"https://pith.science/pith/UXVRMGNGTJAUFRNOYBE3K3B754/action/replication_record"}},"created_at":"2026-07-05T07:58:30.440589+00:00","updated_at":"2026-07-05T07:58:30.440589+00:00"}