{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:DNTKEGPJ2WWTF7QD5Q4KPFXBJS","short_pith_number":"pith:DNTKEGPJ","schema_version":"1.0","canonical_sha256":"1b66a219e9d5ad32fe03ec38a796e14c9555c83dea6cc49a75c1554e386176ce","source":{"kind":"arxiv","id":"2501.08329","version":1},"attestation_state":"computed","paper":{"title":"Predicting 4D Hand Trajectory from Monocular Videos","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haiwen Feng, Michael J. Black, Omid Taheri, Shubham Tulsiani, Yao Feng, Yufei Ye","submitted_at":"2025-01-14T18:59:05Z","abstract_excerpt":"We present HaPTIC, an approach that infers coherent 4D hand trajectories from monocular videos. Current video-based hand pose reconstruction methods primarily focus on improving frame-wise 3D pose using adjacent frames rather than studying consistent 4D hand trajectories in space. Despite the additional temporal cues, they generally underperform compared to image-based methods due to the scarcity of annotated video data. To address these issues, we repurpose a state-of-the-art image-based transformer to take in multiple frames and directly predict a coherent trajectory. We introduce two types "},"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":"2501.08329","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-14T18:59:05Z","cross_cats_sorted":[],"title_canon_sha256":"6d393c865463db6a1f946709e3cf38bae977a239ed80d9fa30f193396c9b535a","abstract_canon_sha256":"a4bc08c34ae3518ef8361b085826620a8010621e3f7493405cbe2d7db6344e49"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:00:59.535240Z","signature_b64":"yUVeoN/RjFk0o0ob3Nkv1kpnxKPloPjdkgfKAQVbb8ltHYvDjFCrxhiIw44w1LMS9pkErrZeG7YBsQYJh/IkCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1b66a219e9d5ad32fe03ec38a796e14c9555c83dea6cc49a75c1554e386176ce","last_reissued_at":"2026-07-05T10:00:59.534834Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:00:59.534834Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Predicting 4D Hand Trajectory from Monocular Videos","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haiwen Feng, Michael J. Black, Omid Taheri, Shubham Tulsiani, Yao Feng, Yufei Ye","submitted_at":"2025-01-14T18:59:05Z","abstract_excerpt":"We present HaPTIC, an approach that infers coherent 4D hand trajectories from monocular videos. Current video-based hand pose reconstruction methods primarily focus on improving frame-wise 3D pose using adjacent frames rather than studying consistent 4D hand trajectories in space. Despite the additional temporal cues, they generally underperform compared to image-based methods due to the scarcity of annotated video data. To address these issues, we repurpose a state-of-the-art image-based transformer to take in multiple frames and directly predict a coherent trajectory. We introduce two types "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.08329","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/2501.08329/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":"2501.08329","created_at":"2026-07-05T10:00:59.534888+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.08329v1","created_at":"2026-07-05T10:00:59.534888+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.08329","created_at":"2026-07-05T10:00:59.534888+00:00"},{"alias_kind":"pith_short_12","alias_value":"DNTKEGPJ2WWT","created_at":"2026-07-05T10:00:59.534888+00:00"},{"alias_kind":"pith_short_16","alias_value":"DNTKEGPJ2WWTF7QD","created_at":"2026-07-05T10:00:59.534888+00:00"},{"alias_kind":"pith_short_8","alias_value":"DNTKEGPJ","created_at":"2026-07-05T10:00:59.534888+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.19156","citing_title":"Hand-4DGS: Feed-Forward 3D Gaussian Splatting for 4D Hand Reconstruction from Egocentric Videos","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2606.10025","citing_title":"GHOST: Hierarchical Sub-Goal Policies for Generalizing Robot Manipulation","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30598","citing_title":"Towards in-the-wild Egocentric 3D Hand-Object Pose Estimation","ref_index":64,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12498","citing_title":"EgoForce: Forearm-Guided Camera-Space 3D Hand Pose from a Monocular Egocentric Camera","ref_index":67,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07642","citing_title":"EggHand: A Multimodal Foundation Model for Egocentric Hand Pose Forecasting","ref_index":47,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DNTKEGPJ2WWTF7QD5Q4KPFXBJS","json":"https://pith.science/pith/DNTKEGPJ2WWTF7QD5Q4KPFXBJS.json","graph_json":"https://pith.science/api/pith-number/DNTKEGPJ2WWTF7QD5Q4KPFXBJS/graph.json","events_json":"https://pith.science/api/pith-number/DNTKEGPJ2WWTF7QD5Q4KPFXBJS/events.json","paper":"https://pith.science/paper/DNTKEGPJ"},"agent_actions":{"view_html":"https://pith.science/pith/DNTKEGPJ2WWTF7QD5Q4KPFXBJS","download_json":"https://pith.science/pith/DNTKEGPJ2WWTF7QD5Q4KPFXBJS.json","view_paper":"https://pith.science/paper/DNTKEGPJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.08329&json=true","fetch_graph":"https://pith.science/api/pith-number/DNTKEGPJ2WWTF7QD5Q4KPFXBJS/graph.json","fetch_events":"https://pith.science/api/pith-number/DNTKEGPJ2WWTF7QD5Q4KPFXBJS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DNTKEGPJ2WWTF7QD5Q4KPFXBJS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DNTKEGPJ2WWTF7QD5Q4KPFXBJS/action/storage_attestation","attest_author":"https://pith.science/pith/DNTKEGPJ2WWTF7QD5Q4KPFXBJS/action/author_attestation","sign_citation":"https://pith.science/pith/DNTKEGPJ2WWTF7QD5Q4KPFXBJS/action/citation_signature","submit_replication":"https://pith.science/pith/DNTKEGPJ2WWTF7QD5Q4KPFXBJS/action/replication_record"}},"created_at":"2026-07-05T10:00:59.534888+00:00","updated_at":"2026-07-05T10:00:59.534888+00:00"}