{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:EWNOIZ5RJPPUSYG3FGD5G4YRYO","short_pith_number":"pith:EWNOIZ5R","schema_version":"1.0","canonical_sha256":"259ae467b14bdf4960db2987d37311c3846bbf8aa532fa4e5fe82c5a4ab55b67","source":{"kind":"arxiv","id":"2410.24211","version":3},"attestation_state":"computed","paper":{"title":"DELTA: Dense Efficient Long-range 3D Tracking for any video","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chaoyang Wang, Chuang Gan, Evangelos Kalogerakis, Hsin-Ying Lee, Peiye Zhuang, Sergey Tulyakov, Tuan Duc Ngo","submitted_at":"2024-10-31T17:59:01Z","abstract_excerpt":"Tracking dense 3D motion from monocular videos remains challenging, particularly when aiming for pixel-level precision over long sequences. We introduce DELTA, a novel method that efficiently tracks every pixel in 3D space, enabling accurate motion estimation across entire videos. Our approach leverages a joint global-local attention mechanism for reduced-resolution tracking, followed by a transformer-based upsampler to achieve high-resolution predictions. Unlike existing methods, which are limited by computational inefficiency or sparse tracking, DELTA delivers dense 3D tracking at scale, run"},"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":"2410.24211","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-31T17:59:01Z","cross_cats_sorted":[],"title_canon_sha256":"38e37d252c873ffdcaf2f512bb4c1eb1d07a0c82dd3c8c3ec54f9a601456f82d","abstract_canon_sha256":"1b215a896318690ac06481a9617e0fb229bc923b50f8283d7f8699f6f2ba8417"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:21:52.159359Z","signature_b64":"js4oGKqMmHAlbHGY3KU3A/CHMyvDs/SNdZEKRMdhrRFNAC7TR11CUS65xx9f/Imtz1Vba5zOLxp6QCt4D16FBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"259ae467b14bdf4960db2987d37311c3846bbf8aa532fa4e5fe82c5a4ab55b67","last_reissued_at":"2026-07-05T10:21:52.158854Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:21:52.158854Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DELTA: Dense Efficient Long-range 3D Tracking for any video","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chaoyang Wang, Chuang Gan, Evangelos Kalogerakis, Hsin-Ying Lee, Peiye Zhuang, Sergey Tulyakov, Tuan Duc Ngo","submitted_at":"2024-10-31T17:59:01Z","abstract_excerpt":"Tracking dense 3D motion from monocular videos remains challenging, particularly when aiming for pixel-level precision over long sequences. We introduce DELTA, a novel method that efficiently tracks every pixel in 3D space, enabling accurate motion estimation across entire videos. Our approach leverages a joint global-local attention mechanism for reduced-resolution tracking, followed by a transformer-based upsampler to achieve high-resolution predictions. Unlike existing methods, which are limited by computational inefficiency or sparse tracking, DELTA delivers dense 3D tracking at scale, run"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.24211","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/2410.24211/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":"2410.24211","created_at":"2026-07-05T10:21:52.158913+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.24211v3","created_at":"2026-07-05T10:21:52.158913+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.24211","created_at":"2026-07-05T10:21:52.158913+00:00"},{"alias_kind":"pith_short_12","alias_value":"EWNOIZ5RJPPU","created_at":"2026-07-05T10:21:52.158913+00:00"},{"alias_kind":"pith_short_16","alias_value":"EWNOIZ5RJPPUSYG3","created_at":"2026-07-05T10:21:52.158913+00:00"},{"alias_kind":"pith_short_8","alias_value":"EWNOIZ5R","created_at":"2026-07-05T10:21:52.158913+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.17303","citing_title":"LongDPM: Overlap-Aware 4D Reconstruction from Long Monocular Videos","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12587","citing_title":"TrackCraft3R: Repurposing Video Diffusion Transformers for Dense 3D Tracking","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04527","citing_title":"Velox: Learning Representations of 4D Geometry and Appearance","ref_index":60,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EWNOIZ5RJPPUSYG3FGD5G4YRYO","json":"https://pith.science/pith/EWNOIZ5RJPPUSYG3FGD5G4YRYO.json","graph_json":"https://pith.science/api/pith-number/EWNOIZ5RJPPUSYG3FGD5G4YRYO/graph.json","events_json":"https://pith.science/api/pith-number/EWNOIZ5RJPPUSYG3FGD5G4YRYO/events.json","paper":"https://pith.science/paper/EWNOIZ5R"},"agent_actions":{"view_html":"https://pith.science/pith/EWNOIZ5RJPPUSYG3FGD5G4YRYO","download_json":"https://pith.science/pith/EWNOIZ5RJPPUSYG3FGD5G4YRYO.json","view_paper":"https://pith.science/paper/EWNOIZ5R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.24211&json=true","fetch_graph":"https://pith.science/api/pith-number/EWNOIZ5RJPPUSYG3FGD5G4YRYO/graph.json","fetch_events":"https://pith.science/api/pith-number/EWNOIZ5RJPPUSYG3FGD5G4YRYO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EWNOIZ5RJPPUSYG3FGD5G4YRYO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EWNOIZ5RJPPUSYG3FGD5G4YRYO/action/storage_attestation","attest_author":"https://pith.science/pith/EWNOIZ5RJPPUSYG3FGD5G4YRYO/action/author_attestation","sign_citation":"https://pith.science/pith/EWNOIZ5RJPPUSYG3FGD5G4YRYO/action/citation_signature","submit_replication":"https://pith.science/pith/EWNOIZ5RJPPUSYG3FGD5G4YRYO/action/replication_record"}},"created_at":"2026-07-05T10:21:52.158913+00:00","updated_at":"2026-07-05T10:21:52.158913+00:00"}