{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:BLLFNGSCDXTJT5FD5FO5FWZIBC","short_pith_number":"pith:BLLFNGSC","schema_version":"1.0","canonical_sha256":"0ad6569a421de699f4a3e95dd2db28089243f161848d52353304c0bad7c7fad9","source":{"kind":"arxiv","id":"2109.10257","version":2},"attestation_state":"computed","paper":{"title":"Skeleton-Graph: Long-Term 3D Motion Prediction From 2D Observations Using Deep Spatio-Temporal Graph CNNs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Abduallah Mohamed, Christian Claudel, Huancheng Chen, Zhangyang Wang","submitted_at":"2021-09-21T15:33:40Z","abstract_excerpt":"Several applications such as autonomous driving, augmented reality and virtual reality require a precise prediction of the 3D human pose. Recently, a new problem was introduced in the field to predict the 3D human poses from observed 2D poses. We propose Skeleton-Graph, a deep spatio-temporal graph CNN model that predicts the future 3D skeleton poses in a single pass from the 2D ones. Unlike prior works, Skeleton-Graph focuses on modeling the interaction between the skeleton joints by exploiting their spatial configuration. This is being achieved by formulating the problem as a graph structure"},"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":"2109.10257","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-09-21T15:33:40Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"dde18c9b19536fbff62e369c06b579ab39149bc94b0da4ffdbd16ac4390a6445","abstract_canon_sha256":"4e378a8669bb442a9c9540a9ca314bab96bda91d78efc9f1e74205b85626601d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:43:44.464220Z","signature_b64":"26tikZahBEWAoGRWjQs4zhMomKnEYYlecvoeW3KX4Lc4UnBGclQjiG/3Phs9mYclIfH9IkU8PK8GN05EzD6/Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0ad6569a421de699f4a3e95dd2db28089243f161848d52353304c0bad7c7fad9","last_reissued_at":"2026-07-05T03:43:44.463760Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:43:44.463760Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Skeleton-Graph: Long-Term 3D Motion Prediction From 2D Observations Using Deep Spatio-Temporal Graph CNNs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Abduallah Mohamed, Christian Claudel, Huancheng Chen, Zhangyang Wang","submitted_at":"2021-09-21T15:33:40Z","abstract_excerpt":"Several applications such as autonomous driving, augmented reality and virtual reality require a precise prediction of the 3D human pose. Recently, a new problem was introduced in the field to predict the 3D human poses from observed 2D poses. We propose Skeleton-Graph, a deep spatio-temporal graph CNN model that predicts the future 3D skeleton poses in a single pass from the 2D ones. Unlike prior works, Skeleton-Graph focuses on modeling the interaction between the skeleton joints by exploiting their spatial configuration. This is being achieved by formulating the problem as a graph structure"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.10257","kind":"arxiv","version":2},"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/2109.10257/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":"2109.10257","created_at":"2026-07-05T03:43:44.463826+00:00"},{"alias_kind":"arxiv_version","alias_value":"2109.10257v2","created_at":"2026-07-05T03:43:44.463826+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.10257","created_at":"2026-07-05T03:43:44.463826+00:00"},{"alias_kind":"pith_short_12","alias_value":"BLLFNGSCDXTJ","created_at":"2026-07-05T03:43:44.463826+00:00"},{"alias_kind":"pith_short_16","alias_value":"BLLFNGSCDXTJT5FD","created_at":"2026-07-05T03:43:44.463826+00:00"},{"alias_kind":"pith_short_8","alias_value":"BLLFNGSC","created_at":"2026-07-05T03:43:44.463826+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.29942","citing_title":"Scene-aware Prediction of Diverse Human Movement Goals","ref_index":27,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BLLFNGSCDXTJT5FD5FO5FWZIBC","json":"https://pith.science/pith/BLLFNGSCDXTJT5FD5FO5FWZIBC.json","graph_json":"https://pith.science/api/pith-number/BLLFNGSCDXTJT5FD5FO5FWZIBC/graph.json","events_json":"https://pith.science/api/pith-number/BLLFNGSCDXTJT5FD5FO5FWZIBC/events.json","paper":"https://pith.science/paper/BLLFNGSC"},"agent_actions":{"view_html":"https://pith.science/pith/BLLFNGSCDXTJT5FD5FO5FWZIBC","download_json":"https://pith.science/pith/BLLFNGSCDXTJT5FD5FO5FWZIBC.json","view_paper":"https://pith.science/paper/BLLFNGSC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2109.10257&json=true","fetch_graph":"https://pith.science/api/pith-number/BLLFNGSCDXTJT5FD5FO5FWZIBC/graph.json","fetch_events":"https://pith.science/api/pith-number/BLLFNGSCDXTJT5FD5FO5FWZIBC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BLLFNGSCDXTJT5FD5FO5FWZIBC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BLLFNGSCDXTJT5FD5FO5FWZIBC/action/storage_attestation","attest_author":"https://pith.science/pith/BLLFNGSCDXTJT5FD5FO5FWZIBC/action/author_attestation","sign_citation":"https://pith.science/pith/BLLFNGSCDXTJT5FD5FO5FWZIBC/action/citation_signature","submit_replication":"https://pith.science/pith/BLLFNGSCDXTJT5FD5FO5FWZIBC/action/replication_record"}},"created_at":"2026-07-05T03:43:44.463826+00:00","updated_at":"2026-07-05T03:43:44.463826+00:00"}