{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:YZL232Z3QMJDGKZ5UNAAEQGQ2U","short_pith_number":"pith:YZL232Z3","schema_version":"1.0","canonical_sha256":"c657adeb3b8312332b3da3400240d0d52ece2b734e68262faf261bed9d0222f2","source":{"kind":"arxiv","id":"2201.02610","version":1},"attestation_state":"computed","paper":{"title":"Embodied Hands: Modeling and Capturing Hands and Bodies Together","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.GR","authors_text":"Dimitrios Tzionas, Javier Romero, Michael J. Black","submitted_at":"2022-01-07T18:59:32Z","abstract_excerpt":"Humans move their hands and bodies together to communicate and solve tasks. Capturing and replicating such coordinated activity is critical for virtual characters that behave realistically. Surprisingly, most methods treat the 3D modeling and tracking of bodies and hands separately. Here we formulate a model of hands and bodies interacting together and fit it to full-body 4D sequences. When scanning or capturing the full body in 3D, hands are small and often partially occluded, making their shape and pose hard to recover. To cope with low-resolution, occlusion, and noise, we develop a new mode"},"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":"2201.02610","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.GR","submitted_at":"2022-01-07T18:59:32Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"092388d514d0197c51e1e5d4af5fe237fa6ea582812725e8e0ae59fc8d9b0b1a","abstract_canon_sha256":"9ef9cac3db988e5c4fecf7c5e022e3154e59e28cb6809e385407ca0f901ed9b7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:46:42.618413Z","signature_b64":"ntlMhyyJYs6sj6MNBFxS2t/TF3dRfUdtUUBJ807C3IOu7DlK6f0vdp5T4EVknEQdyfRuZQsYc89NQPcPvHADCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c657adeb3b8312332b3da3400240d0d52ece2b734e68262faf261bed9d0222f2","last_reissued_at":"2026-07-05T03:46:42.618001Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:46:42.618001Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Embodied Hands: Modeling and Capturing Hands and Bodies Together","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.GR","authors_text":"Dimitrios Tzionas, Javier Romero, Michael J. Black","submitted_at":"2022-01-07T18:59:32Z","abstract_excerpt":"Humans move their hands and bodies together to communicate and solve tasks. Capturing and replicating such coordinated activity is critical for virtual characters that behave realistically. Surprisingly, most methods treat the 3D modeling and tracking of bodies and hands separately. Here we formulate a model of hands and bodies interacting together and fit it to full-body 4D sequences. When scanning or capturing the full body in 3D, hands are small and often partially occluded, making their shape and pose hard to recover. To cope with low-resolution, occlusion, and noise, we develop a new mode"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.02610","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/2201.02610/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":"2201.02610","created_at":"2026-07-05T03:46:42.618059+00:00"},{"alias_kind":"arxiv_version","alias_value":"2201.02610v1","created_at":"2026-07-05T03:46:42.618059+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.02610","created_at":"2026-07-05T03:46:42.618059+00:00"},{"alias_kind":"pith_short_12","alias_value":"YZL232Z3QMJD","created_at":"2026-07-05T03:46:42.618059+00:00"},{"alias_kind":"pith_short_16","alias_value":"YZL232Z3QMJDGKZ5","created_at":"2026-07-05T03:46:42.618059+00:00"},{"alias_kind":"pith_short_8","alias_value":"YZL232Z3","created_at":"2026-07-05T03:46:42.618059+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":34,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22806","citing_title":"Policy-as-Data: Learning Generalizable HOI Diffusion Models from Simulated Physics","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2606.22718","citing_title":"Generative Relightable Avatars","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2606.17846","citing_title":"Qwen-RobotManip Technical Report: Alignment Unlocks Scale for Robotic Manipulation Foundation Models","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2606.15966","citing_title":"VEPHand: View-Efficient Photometric Hand Performance Capture at Scale","ref_index":65,"is_internal_anchor":false},{"citing_arxiv_id":"2607.01768","citing_title":"JointHOI: Jointly Generating Contact Maps Enhances Hand Object Interaction Generation","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2606.10743","citing_title":"Hand-centric Human-to-Robot Trajectory Transfer from Video Demonstrations via Open-World Contact Localization","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2606.10614","citing_title":"Dexterous Point Policy: Learning Point-based Dexterous Hand Policies from Human Demonstrations","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29686","citing_title":"PoseShield: Neural Collision Fields for Human Self-Collision Resolution","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2606.06872","citing_title":"EgoPressDiff: Multimodal Video Diffusion for Egocentric UV-Domain Hand-Pressure Estimation","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2607.01067","citing_title":"Human-Centric Transferable Tactile Pre-Training for Dexterous Robotic Manipulation","ref_index":52,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03268","citing_title":"EaDex: A Cross-Embodiment Dexterous Manipulation Framework from Low-Cost Demonstrations","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2605.31234","citing_title":"HARP-VLA: Human-Robot Aligned Representation Learning for Vision-Language-Action Model","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28133","citing_title":"Translation as a Bridging Action: Transferring Manipulation Skills from Humans to Robots","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15477","citing_title":"EgoExo-WM: Unlocking Exo Video for Ego World Models","ref_index":63,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29686","citing_title":"PoseShield: Neural Collision Fields for Human Self-Collision Resolution","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23555","citing_title":"Generator-Refiner-Examiner: A Tri-Module Data Augmentation Framework for 3D Human Avatar Learning from Monocular Videos","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2503.09640","citing_title":"Physically Plausible Human-Object Rendering from Sparse Views via 3D Gaussian Splatting","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24681","citing_title":"Learning Human-Intention Priors from Large-Scale Human Demonstrations for Robotic Manipulation","ref_index":52,"is_internal_anchor":false},{"citing_arxiv_id":"2511.18127","citing_title":"SFHand: Learning Embodied Manipulation by Streaming Egocentric 3D Hand Forecasting","ref_index":67,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17354","citing_title":"GeoHand: Unlocking Prior Geometry Knowledge for Monocular 3D Hand Reconstruction","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17638","citing_title":"TouchMap-OR: Multi-View 3D Mapping of Hand-Surface Contacts","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17742","citing_title":"UST-Hand: An Uncertainty-aware Spatiotemporal Point Cloud Interaction Network for 3D Self-supervised Hand Pose Estimation","ref_index":52,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15477","citing_title":"EgoExo-WM: Unlocking Exo Video for Ego World Models","ref_index":63,"is_internal_anchor":false},{"citing_arxiv_id":"2506.02618","citing_title":"Rodrigues Network for Learning Robot Actions","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2511.12878","citing_title":"Uni-Hand: Universal Hand Motion Forecasting in Egocentric Views","ref_index":77,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YZL232Z3QMJDGKZ5UNAAEQGQ2U","json":"https://pith.science/pith/YZL232Z3QMJDGKZ5UNAAEQGQ2U.json","graph_json":"https://pith.science/api/pith-number/YZL232Z3QMJDGKZ5UNAAEQGQ2U/graph.json","events_json":"https://pith.science/api/pith-number/YZL232Z3QMJDGKZ5UNAAEQGQ2U/events.json","paper":"https://pith.science/paper/YZL232Z3"},"agent_actions":{"view_html":"https://pith.science/pith/YZL232Z3QMJDGKZ5UNAAEQGQ2U","download_json":"https://pith.science/pith/YZL232Z3QMJDGKZ5UNAAEQGQ2U.json","view_paper":"https://pith.science/paper/YZL232Z3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2201.02610&json=true","fetch_graph":"https://pith.science/api/pith-number/YZL232Z3QMJDGKZ5UNAAEQGQ2U/graph.json","fetch_events":"https://pith.science/api/pith-number/YZL232Z3QMJDGKZ5UNAAEQGQ2U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YZL232Z3QMJDGKZ5UNAAEQGQ2U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YZL232Z3QMJDGKZ5UNAAEQGQ2U/action/storage_attestation","attest_author":"https://pith.science/pith/YZL232Z3QMJDGKZ5UNAAEQGQ2U/action/author_attestation","sign_citation":"https://pith.science/pith/YZL232Z3QMJDGKZ5UNAAEQGQ2U/action/citation_signature","submit_replication":"https://pith.science/pith/YZL232Z3QMJDGKZ5UNAAEQGQ2U/action/replication_record"}},"created_at":"2026-07-05T03:46:42.618059+00:00","updated_at":"2026-07-05T03:46:42.618059+00:00"}