{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:CDRA2JUZRZYB4CVGA3423HJI63","short_pith_number":"pith:CDRA2JUZ","schema_version":"1.0","canonical_sha256":"10e20d26998e701e0aa606f9ad9d28f6d990efe591f8d915fe647632cb3f25b4","source":{"kind":"arxiv","id":"2407.05921","version":2},"attestation_state":"computed","paper":{"title":"TAPVid-3D: A Benchmark for Tracking Any Point in 3D","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Andrew Zisserman, Carl Doersch, Gabriel Brostow, Ignacio Rocco, Jo\\~ao Carreira, Joe Heyward, Skanda Koppula, Yi Yang","submitted_at":"2024-07-08T13:28:47Z","abstract_excerpt":"We introduce a new benchmark, TAPVid-3D, for evaluating the task of long-range Tracking Any Point in 3D (TAP-3D). While point tracking in two dimensions (TAP) has many benchmarks measuring performance on real-world videos, such as TAPVid-DAVIS, three-dimensional point tracking has none. To this end, leveraging existing footage, we build a new benchmark for 3D point tracking featuring 4,000+ real-world videos, composed of three different data sources spanning a variety of object types, motion patterns, and indoor and outdoor environments. To measure performance on the TAP-3D task, we formulate "},"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":"2407.05921","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-08T13:28:47Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"f15a5659489b92da81da8f46535ff5345ec9146734c145aad02abd9ebd54b8e5","abstract_canon_sha256":"2b8cee6848a8e8a3f8b3ddabfe481d2bcef4384621c8c284babc2436b622059e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:59:53.071861Z","signature_b64":"OR7LxpX99E7zfyTyEWOteUrVgcq7nwpA9lebuO7NgbU0fiWtHEPYTOJMg7hxN1y7haxr1V9iPSvMEk5FfFqlAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"10e20d26998e701e0aa606f9ad9d28f6d990efe591f8d915fe647632cb3f25b4","last_reissued_at":"2026-07-05T08:59:53.071424Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:59:53.071424Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TAPVid-3D: A Benchmark for Tracking Any Point in 3D","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Andrew Zisserman, Carl Doersch, Gabriel Brostow, Ignacio Rocco, Jo\\~ao Carreira, Joe Heyward, Skanda Koppula, Yi Yang","submitted_at":"2024-07-08T13:28:47Z","abstract_excerpt":"We introduce a new benchmark, TAPVid-3D, for evaluating the task of long-range Tracking Any Point in 3D (TAP-3D). While point tracking in two dimensions (TAP) has many benchmarks measuring performance on real-world videos, such as TAPVid-DAVIS, three-dimensional point tracking has none. To this end, leveraging existing footage, we build a new benchmark for 3D point tracking featuring 4,000+ real-world videos, composed of three different data sources spanning a variety of object types, motion patterns, and indoor and outdoor environments. To measure performance on the TAP-3D task, we formulate "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.05921","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/2407.05921/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":"2407.05921","created_at":"2026-07-05T08:59:53.071486+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.05921v2","created_at":"2026-07-05T08:59:53.071486+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.05921","created_at":"2026-07-05T08:59:53.071486+00:00"},{"alias_kind":"pith_short_12","alias_value":"CDRA2JUZRZYB","created_at":"2026-07-05T08:59:53.071486+00:00"},{"alias_kind":"pith_short_16","alias_value":"CDRA2JUZRZYB4CVG","created_at":"2026-07-05T08:59:53.071486+00:00"},{"alias_kind":"pith_short_8","alias_value":"CDRA2JUZ","created_at":"2026-07-05T08:59:53.071486+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.22160","citing_title":"GenMatter: Perceiving Physical Objects with Generative Matter Models","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2505.17015","citing_title":"Multi-SpatialMLLM: Multi-Frame Spatial Understanding with Multi-Modal Large Language Models","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22160","citing_title":"GenMatter: Perceiving Physical Objects with Generative Matter Models","ref_index":33,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CDRA2JUZRZYB4CVGA3423HJI63","json":"https://pith.science/pith/CDRA2JUZRZYB4CVGA3423HJI63.json","graph_json":"https://pith.science/api/pith-number/CDRA2JUZRZYB4CVGA3423HJI63/graph.json","events_json":"https://pith.science/api/pith-number/CDRA2JUZRZYB4CVGA3423HJI63/events.json","paper":"https://pith.science/paper/CDRA2JUZ"},"agent_actions":{"view_html":"https://pith.science/pith/CDRA2JUZRZYB4CVGA3423HJI63","download_json":"https://pith.science/pith/CDRA2JUZRZYB4CVGA3423HJI63.json","view_paper":"https://pith.science/paper/CDRA2JUZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.05921&json=true","fetch_graph":"https://pith.science/api/pith-number/CDRA2JUZRZYB4CVGA3423HJI63/graph.json","fetch_events":"https://pith.science/api/pith-number/CDRA2JUZRZYB4CVGA3423HJI63/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CDRA2JUZRZYB4CVGA3423HJI63/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CDRA2JUZRZYB4CVGA3423HJI63/action/storage_attestation","attest_author":"https://pith.science/pith/CDRA2JUZRZYB4CVGA3423HJI63/action/author_attestation","sign_citation":"https://pith.science/pith/CDRA2JUZRZYB4CVGA3423HJI63/action/citation_signature","submit_replication":"https://pith.science/pith/CDRA2JUZRZYB4CVGA3423HJI63/action/replication_record"}},"created_at":"2026-07-05T08:59:53.071486+00:00","updated_at":"2026-07-05T08:59:53.071486+00:00"}