{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:HL6UKFO2OQ6OPOKF6LSXBHCHNH","short_pith_number":"pith:HL6UKFO2","schema_version":"1.0","canonical_sha256":"3afd4515da743ce7b945f2e5709c4769d1c957768779fefa6cf7ceab4cc25e12","source":{"kind":"arxiv","id":"2103.10455","version":3},"attestation_state":"computed","paper":{"title":"3D Human Pose Estimation with Spatial and Temporal Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.HC"],"primary_cat":"cs.CV","authors_text":"Ce Zheng, Chen Chen, Matias Mendieta, Sijie Zhu, Taojiannan Yang, Zhengming Ding","submitted_at":"2021-03-18T18:14:37Z","abstract_excerpt":"Transformer architectures have become the model of choice in natural language processing and are now being introduced into computer vision tasks such as image classification, object detection, and semantic segmentation. However, in the field of human pose estimation, convolutional architectures still remain dominant. In this work, we present PoseFormer, a purely transformer-based approach for 3D human pose estimation in videos without convolutional architectures involved. Inspired by recent developments in vision transformers, we design a spatial-temporal transformer structure to comprehensive"},"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":"2103.10455","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-03-18T18:14:37Z","cross_cats_sorted":["cs.AI","cs.HC"],"title_canon_sha256":"4f0aaf8ce7ccf5c715f261fd4e4d3d4485d57b3cd63163f949a893e2023a5805","abstract_canon_sha256":"874432d24d7773ac19fb9134e7f8ef9eb6382691815aa40226f8e2fd94cee782"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:07:47.692488Z","signature_b64":"vTKZXu8EFt4yOOJiDgoaUpKYbeeckTdOzS8QhOFwUMmxkoT0VWoFO8ufP/3s5HOcyn+Pdy1a7vQ6lF74bOkkAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3afd4515da743ce7b945f2e5709c4769d1c957768779fefa6cf7ceab4cc25e12","last_reissued_at":"2026-07-05T03:07:47.692011Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:07:47.692011Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"3D Human Pose Estimation with Spatial and Temporal Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.HC"],"primary_cat":"cs.CV","authors_text":"Ce Zheng, Chen Chen, Matias Mendieta, Sijie Zhu, Taojiannan Yang, Zhengming Ding","submitted_at":"2021-03-18T18:14:37Z","abstract_excerpt":"Transformer architectures have become the model of choice in natural language processing and are now being introduced into computer vision tasks such as image classification, object detection, and semantic segmentation. However, in the field of human pose estimation, convolutional architectures still remain dominant. In this work, we present PoseFormer, a purely transformer-based approach for 3D human pose estimation in videos without convolutional architectures involved. Inspired by recent developments in vision transformers, we design a spatial-temporal transformer structure to comprehensive"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.10455","kind":"arxiv","version":3},"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/2103.10455/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":"2103.10455","created_at":"2026-07-05T03:07:47.692067+00:00"},{"alias_kind":"arxiv_version","alias_value":"2103.10455v3","created_at":"2026-07-05T03:07:47.692067+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.10455","created_at":"2026-07-05T03:07:47.692067+00:00"},{"alias_kind":"pith_short_12","alias_value":"HL6UKFO2OQ6O","created_at":"2026-07-05T03:07:47.692067+00:00"},{"alias_kind":"pith_short_16","alias_value":"HL6UKFO2OQ6OPOKF","created_at":"2026-07-05T03:07:47.692067+00:00"},{"alias_kind":"pith_short_8","alias_value":"HL6UKFO2","created_at":"2026-07-05T03:07:47.692067+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.17688","citing_title":"Dual-stream Spatio-Temporal GCN-Transformer Network for 3D Human Pose Estimation","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HL6UKFO2OQ6OPOKF6LSXBHCHNH","json":"https://pith.science/pith/HL6UKFO2OQ6OPOKF6LSXBHCHNH.json","graph_json":"https://pith.science/api/pith-number/HL6UKFO2OQ6OPOKF6LSXBHCHNH/graph.json","events_json":"https://pith.science/api/pith-number/HL6UKFO2OQ6OPOKF6LSXBHCHNH/events.json","paper":"https://pith.science/paper/HL6UKFO2"},"agent_actions":{"view_html":"https://pith.science/pith/HL6UKFO2OQ6OPOKF6LSXBHCHNH","download_json":"https://pith.science/pith/HL6UKFO2OQ6OPOKF6LSXBHCHNH.json","view_paper":"https://pith.science/paper/HL6UKFO2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2103.10455&json=true","fetch_graph":"https://pith.science/api/pith-number/HL6UKFO2OQ6OPOKF6LSXBHCHNH/graph.json","fetch_events":"https://pith.science/api/pith-number/HL6UKFO2OQ6OPOKF6LSXBHCHNH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HL6UKFO2OQ6OPOKF6LSXBHCHNH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HL6UKFO2OQ6OPOKF6LSXBHCHNH/action/storage_attestation","attest_author":"https://pith.science/pith/HL6UKFO2OQ6OPOKF6LSXBHCHNH/action/author_attestation","sign_citation":"https://pith.science/pith/HL6UKFO2OQ6OPOKF6LSXBHCHNH/action/citation_signature","submit_replication":"https://pith.science/pith/HL6UKFO2OQ6OPOKF6LSXBHCHNH/action/replication_record"}},"created_at":"2026-07-05T03:07:47.692067+00:00","updated_at":"2026-07-05T03:07:47.692067+00:00"}