{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:PRRN2TJBYTEYOQQ6JUE73GOXJU","short_pith_number":"pith:PRRN2TJB","schema_version":"1.0","canonical_sha256":"7c62dd4d21c4c987421e4d09fd99d74d1649c6323089610e3f2e53a923438087","source":{"kind":"arxiv","id":"1711.08996","version":1},"attestation_state":"computed","paper":{"title":"Dense 3D Regression for Hand Pose Estimation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Angela Yao, Chengde Wan, Luc Van Gool, Thomas Probst","submitted_at":"2017-11-24T14:50:23Z","abstract_excerpt":"We present a simple and effective method for 3D hand pose estimation from a single depth frame. As opposed to previous state-of-the-art methods based on holistic 3D regression, our method works on dense pixel-wise estimation. This is achieved by careful design choices in pose parameterization, which leverages both 2D and 3D properties of depth map. Specifically, we decompose the pose parameters into a set of per-pixel estimations, i.e., 2D heat maps, 3D heat maps and unit 3D directional vector fields. The 2D/3D joint heat maps and 3D joint offsets are estimated via multi-task network cascades,"},"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":"1711.08996","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-11-24T14:50:23Z","cross_cats_sorted":[],"title_canon_sha256":"bd0f67690997f0831349c6e40e06e31814982909e35a6f2cdd388a229d30a33c","abstract_canon_sha256":"12e99ba8edd7b4648db4ebe014ffdce9e3bf546b35a2b09ed232a30710539abf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:29:41.531174Z","signature_b64":"0ZoqgUpasX4CcoRMINDwKK0V0oUr1ckkAZ6u3JMqOdmavrMqRV+k4nobsSUT+1TKpwNDqpicTlwlUQHh7JOVAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7c62dd4d21c4c987421e4d09fd99d74d1649c6323089610e3f2e53a923438087","last_reissued_at":"2026-05-18T00:29:41.530687Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:29:41.530687Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dense 3D Regression for Hand Pose Estimation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Angela Yao, Chengde Wan, Luc Van Gool, Thomas Probst","submitted_at":"2017-11-24T14:50:23Z","abstract_excerpt":"We present a simple and effective method for 3D hand pose estimation from a single depth frame. As opposed to previous state-of-the-art methods based on holistic 3D regression, our method works on dense pixel-wise estimation. This is achieved by careful design choices in pose parameterization, which leverages both 2D and 3D properties of depth map. Specifically, we decompose the pose parameters into a set of per-pixel estimations, i.e., 2D heat maps, 3D heat maps and unit 3D directional vector fields. The 2D/3D joint heat maps and 3D joint offsets are estimated via multi-task network cascades,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.08996","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":""},"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":"1711.08996","created_at":"2026-05-18T00:29:41.530772+00:00"},{"alias_kind":"arxiv_version","alias_value":"1711.08996v1","created_at":"2026-05-18T00:29:41.530772+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.08996","created_at":"2026-05-18T00:29:41.530772+00:00"},{"alias_kind":"pith_short_12","alias_value":"PRRN2TJBYTEY","created_at":"2026-05-18T12:31:37.085036+00:00"},{"alias_kind":"pith_short_16","alias_value":"PRRN2TJBYTEYOQQ6","created_at":"2026-05-18T12:31:37.085036+00:00"},{"alias_kind":"pith_short_8","alias_value":"PRRN2TJB","created_at":"2026-05-18T12:31:37.085036+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PRRN2TJBYTEYOQQ6JUE73GOXJU","json":"https://pith.science/pith/PRRN2TJBYTEYOQQ6JUE73GOXJU.json","graph_json":"https://pith.science/api/pith-number/PRRN2TJBYTEYOQQ6JUE73GOXJU/graph.json","events_json":"https://pith.science/api/pith-number/PRRN2TJBYTEYOQQ6JUE73GOXJU/events.json","paper":"https://pith.science/paper/PRRN2TJB"},"agent_actions":{"view_html":"https://pith.science/pith/PRRN2TJBYTEYOQQ6JUE73GOXJU","download_json":"https://pith.science/pith/PRRN2TJBYTEYOQQ6JUE73GOXJU.json","view_paper":"https://pith.science/paper/PRRN2TJB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1711.08996&json=true","fetch_graph":"https://pith.science/api/pith-number/PRRN2TJBYTEYOQQ6JUE73GOXJU/graph.json","fetch_events":"https://pith.science/api/pith-number/PRRN2TJBYTEYOQQ6JUE73GOXJU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PRRN2TJBYTEYOQQ6JUE73GOXJU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PRRN2TJBYTEYOQQ6JUE73GOXJU/action/storage_attestation","attest_author":"https://pith.science/pith/PRRN2TJBYTEYOQQ6JUE73GOXJU/action/author_attestation","sign_citation":"https://pith.science/pith/PRRN2TJBYTEYOQQ6JUE73GOXJU/action/citation_signature","submit_replication":"https://pith.science/pith/PRRN2TJBYTEYOQQ6JUE73GOXJU/action/replication_record"}},"created_at":"2026-05-18T00:29:41.530772+00:00","updated_at":"2026-05-18T00:29:41.530772+00:00"}