{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:VPXDQPKL637CICS4XEVRXOZ4TJ","short_pith_number":"pith:VPXDQPKL","schema_version":"1.0","canonical_sha256":"abee383d4bf6fe240a5cb92b1bbb3c9a74a142fd193df1cf8c64370475874db4","source":{"kind":"arxiv","id":"2407.16291","version":2},"attestation_state":"computed","paper":{"title":"TAPTRv2: Attention-based Position Update Improves Tracking Any Point","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Bohan Li, Feng Li, Hao Zhang, Hongyang Li, Lei Zhang, Shilong Liu, Tianhe Ren, Zhaoyang Zeng","submitted_at":"2024-07-23T08:46:14Z","abstract_excerpt":"In this paper, we present TAPTRv2, a Transformer-based approach built upon TAPTR for solving the Tracking Any Point (TAP) task. TAPTR borrows designs from DEtection TRansformer (DETR) and formulates each tracking point as a point query, making it possible to leverage well-studied operations in DETR-like algorithms. TAPTRv2 improves TAPTR by addressing a critical issue regarding its reliance on cost-volume,which contaminates the point query\\'s content feature and negatively impacts both visibility prediction and cost-volume computation. In TAPTRv2, we propose a novel attention-based position up"},"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":"2407.16291","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-23T08:46:14Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"1c4fe99a28b2ce029bd5fc2e5da7962b046a7567174e2238f1d97627f0b13183","abstract_canon_sha256":"c4c1bfaf2b5012cb2f8b9f663d32379d2ff7aacc339918e93d5a323a6647fdeb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:00:38.068086Z","signature_b64":"buqFszTsawcrqyQFDuuLeaPy2wVS/OG9liI9VRSFxgsMXtAeOpAbT7gHNG+MX+h7mgCYDC5Th7AafcuPNYV9BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"abee383d4bf6fe240a5cb92b1bbb3c9a74a142fd193df1cf8c64370475874db4","last_reissued_at":"2026-07-05T11:00:38.067608Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:00:38.067608Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TAPTRv2: Attention-based Position Update Improves Tracking Any Point","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Bohan Li, Feng Li, Hao Zhang, Hongyang Li, Lei Zhang, Shilong Liu, Tianhe Ren, Zhaoyang Zeng","submitted_at":"2024-07-23T08:46:14Z","abstract_excerpt":"In this paper, we present TAPTRv2, a Transformer-based approach built upon TAPTR for solving the Tracking Any Point (TAP) task. TAPTR borrows designs from DEtection TRansformer (DETR) and formulates each tracking point as a point query, making it possible to leverage well-studied operations in DETR-like algorithms. TAPTRv2 improves TAPTR by addressing a critical issue regarding its reliance on cost-volume,which contaminates the point query\\'s content feature and negatively impacts both visibility prediction and cost-volume computation. In TAPTRv2, we propose a novel attention-based position up"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.16291","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/2407.16291/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":"2407.16291","created_at":"2026-07-05T11:00:38.067661+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.16291v2","created_at":"2026-07-05T11:00:38.067661+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.16291","created_at":"2026-07-05T11:00:38.067661+00:00"},{"alias_kind":"pith_short_12","alias_value":"VPXDQPKL637C","created_at":"2026-07-05T11:00:38.067661+00:00"},{"alias_kind":"pith_short_16","alias_value":"VPXDQPKL637CICS4","created_at":"2026-07-05T11:00:38.067661+00:00"},{"alias_kind":"pith_short_8","alias_value":"VPXDQPKL","created_at":"2026-07-05T11:00:38.067661+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.03220","citing_title":"ProTracker: Probabilistic Integration for Robust and Accurate Point Tracking","ref_index":26,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VPXDQPKL637CICS4XEVRXOZ4TJ","json":"https://pith.science/pith/VPXDQPKL637CICS4XEVRXOZ4TJ.json","graph_json":"https://pith.science/api/pith-number/VPXDQPKL637CICS4XEVRXOZ4TJ/graph.json","events_json":"https://pith.science/api/pith-number/VPXDQPKL637CICS4XEVRXOZ4TJ/events.json","paper":"https://pith.science/paper/VPXDQPKL"},"agent_actions":{"view_html":"https://pith.science/pith/VPXDQPKL637CICS4XEVRXOZ4TJ","download_json":"https://pith.science/pith/VPXDQPKL637CICS4XEVRXOZ4TJ.json","view_paper":"https://pith.science/paper/VPXDQPKL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.16291&json=true","fetch_graph":"https://pith.science/api/pith-number/VPXDQPKL637CICS4XEVRXOZ4TJ/graph.json","fetch_events":"https://pith.science/api/pith-number/VPXDQPKL637CICS4XEVRXOZ4TJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VPXDQPKL637CICS4XEVRXOZ4TJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VPXDQPKL637CICS4XEVRXOZ4TJ/action/storage_attestation","attest_author":"https://pith.science/pith/VPXDQPKL637CICS4XEVRXOZ4TJ/action/author_attestation","sign_citation":"https://pith.science/pith/VPXDQPKL637CICS4XEVRXOZ4TJ/action/citation_signature","submit_replication":"https://pith.science/pith/VPXDQPKL637CICS4XEVRXOZ4TJ/action/replication_record"}},"created_at":"2026-07-05T11:00:38.067661+00:00","updated_at":"2026-07-05T11:00:38.067661+00:00"}