{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:YPIDJXI2B56NJTJ5KRO7NLVQAD","short_pith_number":"pith:YPIDJXI2","schema_version":"1.0","canonical_sha256":"c3d034dd1a0f7cd4cd3d545df6aeb000fdf4076bf8eef0564d2ac216f779262e","source":{"kind":"arxiv","id":"2406.06843","version":4},"attestation_state":"computed","paper":{"title":"HO-Cap: A Capture System and Dataset for 3D Reconstruction and Pose Tracking of Hand-Object Interaction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bowen Wen, Jikai Wang, Qifan Zhang, Xiaohu Guo, Yu-Wei Chao, Yu Xiang","submitted_at":"2024-06-10T23:25:19Z","abstract_excerpt":"We introduce a data capture system and a new dataset, HO-Cap, for 3D reconstruction and pose tracking of hands and objects in videos. The system leverages multiple RGBD cameras and a HoloLens headset for data collection, avoiding the use of expensive 3D scanners or mocap systems. We propose a semi-automatic method for annotating the shape and pose of hands and objects in the collected videos, significantly reducing the annotation time compared to manual labeling. With this system, we captured a video dataset of humans interacting with objects to perform various tasks, including simple pick-and"},"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":"2406.06843","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-10T23:25:19Z","cross_cats_sorted":[],"title_canon_sha256":"cb2804970d70ba1b455516f1377a1f854151d8d0f106689a50f732f2b2c91f09","abstract_canon_sha256":"8ffa2131dc78699a282f0e7911c1f6e450eb769d5ae08ce316e5470424250575"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:28:17.574653Z","signature_b64":"7glplQVrV8uFeqeglAbjOEpR06SS/NNPa4PmRQPTDn7kivGSf3zyLnd1N+22bFIzLqDRrgLbb9UDph5eKKpZCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c3d034dd1a0f7cd4cd3d545df6aeb000fdf4076bf8eef0564d2ac216f779262e","last_reissued_at":"2026-07-05T10:28:17.574142Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:28:17.574142Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HO-Cap: A Capture System and Dataset for 3D Reconstruction and Pose Tracking of Hand-Object Interaction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bowen Wen, Jikai Wang, Qifan Zhang, Xiaohu Guo, Yu-Wei Chao, Yu Xiang","submitted_at":"2024-06-10T23:25:19Z","abstract_excerpt":"We introduce a data capture system and a new dataset, HO-Cap, for 3D reconstruction and pose tracking of hands and objects in videos. The system leverages multiple RGBD cameras and a HoloLens headset for data collection, avoiding the use of expensive 3D scanners or mocap systems. We propose a semi-automatic method for annotating the shape and pose of hands and objects in the collected videos, significantly reducing the annotation time compared to manual labeling. With this system, we captured a video dataset of humans interacting with objects to perform various tasks, including simple pick-and"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.06843","kind":"arxiv","version":4},"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/2406.06843/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":"2406.06843","created_at":"2026-07-05T10:28:17.574202+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.06843v4","created_at":"2026-07-05T10:28:17.574202+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.06843","created_at":"2026-07-05T10:28:17.574202+00:00"},{"alias_kind":"pith_short_12","alias_value":"YPIDJXI2B56N","created_at":"2026-07-05T10:28:17.574202+00:00"},{"alias_kind":"pith_short_16","alias_value":"YPIDJXI2B56NJTJ5","created_at":"2026-07-05T10:28:17.574202+00:00"},{"alias_kind":"pith_short_8","alias_value":"YPIDJXI2","created_at":"2026-07-05T10:28:17.574202+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2510.26433","citing_title":"Co-Evolving Latent Action World Models","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2507.23682","citing_title":"villa-X: Enhancing Latent Action Modeling in Vision-Language-Action Models","ref_index":63,"is_internal_anchor":false},{"citing_arxiv_id":"2603.28045","citing_title":"Event6D: Event-based Novel Object 6D Pose Tracking","ref_index":129,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09535","citing_title":"EgoTL: Egocentric Think-Aloud Chains for Long-Horizon Tasks","ref_index":47,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YPIDJXI2B56NJTJ5KRO7NLVQAD","json":"https://pith.science/pith/YPIDJXI2B56NJTJ5KRO7NLVQAD.json","graph_json":"https://pith.science/api/pith-number/YPIDJXI2B56NJTJ5KRO7NLVQAD/graph.json","events_json":"https://pith.science/api/pith-number/YPIDJXI2B56NJTJ5KRO7NLVQAD/events.json","paper":"https://pith.science/paper/YPIDJXI2"},"agent_actions":{"view_html":"https://pith.science/pith/YPIDJXI2B56NJTJ5KRO7NLVQAD","download_json":"https://pith.science/pith/YPIDJXI2B56NJTJ5KRO7NLVQAD.json","view_paper":"https://pith.science/paper/YPIDJXI2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.06843&json=true","fetch_graph":"https://pith.science/api/pith-number/YPIDJXI2B56NJTJ5KRO7NLVQAD/graph.json","fetch_events":"https://pith.science/api/pith-number/YPIDJXI2B56NJTJ5KRO7NLVQAD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YPIDJXI2B56NJTJ5KRO7NLVQAD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YPIDJXI2B56NJTJ5KRO7NLVQAD/action/storage_attestation","attest_author":"https://pith.science/pith/YPIDJXI2B56NJTJ5KRO7NLVQAD/action/author_attestation","sign_citation":"https://pith.science/pith/YPIDJXI2B56NJTJ5KRO7NLVQAD/action/citation_signature","submit_replication":"https://pith.science/pith/YPIDJXI2B56NJTJ5KRO7NLVQAD/action/replication_record"}},"created_at":"2026-07-05T10:28:17.574202+00:00","updated_at":"2026-07-05T10:28:17.574202+00:00"}