{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:GCLEV747KX77TVF2YK5RSLY5AH","short_pith_number":"pith:GCLEV747","schema_version":"1.0","canonical_sha256":"30964aff9f55fff9d4bac2bb192f1d01dd5ec712c21947143555bec200338388","source":{"kind":"arxiv","id":"2301.07322","version":1},"attestation_state":"computed","paper":{"title":"HSTFormer: Hierarchical Spatial-Temporal Transformers for 3D Human Pose Estimation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jing Xiao, Mei Han, Ming-Chun Huang, Ning Zhang, Ruei-Sung Lin, Xiaoye Qian, Youbao Tang","submitted_at":"2023-01-18T05:54:02Z","abstract_excerpt":"Transformer-based approaches have been successfully proposed for 3D human pose estimation (HPE) from 2D pose sequence and achieved state-of-the-art (SOTA) performance. However, current SOTAs have difficulties in modeling spatial-temporal correlations of joints at different levels simultaneously. This is due to the poses' spatial-temporal complexity. Poses move at various speeds temporarily with various joints and body-parts movement spatially. Hence, a cookie-cutter transformer is non-adaptable and can hardly meet the \"in-the-wild\" requirement. To mitigate this issue, we propose Hierarchical S"},"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":"2301.07322","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-01-18T05:54:02Z","cross_cats_sorted":[],"title_canon_sha256":"bef979b385f3611da09d2aa26fd45d70fbc2e10e10ca883b43905cc4f5e5b641","abstract_canon_sha256":"0a79cb2725c0ec1df48a2e35eee5366acd726374f150af45227510b8dfd65d01"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:34:07.671221Z","signature_b64":"SCAH1p+qaLUe3tl1mJeh8Op84E+/jAudBqeHdA196M1x4HmwF8SvcEnYhX9XLYC6Rg9xfo9DVq2WmR1DBTYxAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"30964aff9f55fff9d4bac2bb192f1d01dd5ec712c21947143555bec200338388","last_reissued_at":"2026-07-05T05:34:07.670809Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:34:07.670809Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HSTFormer: Hierarchical Spatial-Temporal Transformers for 3D Human Pose Estimation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jing Xiao, Mei Han, Ming-Chun Huang, Ning Zhang, Ruei-Sung Lin, Xiaoye Qian, Youbao Tang","submitted_at":"2023-01-18T05:54:02Z","abstract_excerpt":"Transformer-based approaches have been successfully proposed for 3D human pose estimation (HPE) from 2D pose sequence and achieved state-of-the-art (SOTA) performance. However, current SOTAs have difficulties in modeling spatial-temporal correlations of joints at different levels simultaneously. This is due to the poses' spatial-temporal complexity. Poses move at various speeds temporarily with various joints and body-parts movement spatially. Hence, a cookie-cutter transformer is non-adaptable and can hardly meet the \"in-the-wild\" requirement. To mitigate this issue, we propose Hierarchical S"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.07322","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/2301.07322/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":"2301.07322","created_at":"2026-07-05T05:34:07.670871+00:00"},{"alias_kind":"arxiv_version","alias_value":"2301.07322v1","created_at":"2026-07-05T05:34:07.670871+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.07322","created_at":"2026-07-05T05:34:07.670871+00:00"},{"alias_kind":"pith_short_12","alias_value":"GCLEV747KX77","created_at":"2026-07-05T05:34:07.670871+00:00"},{"alias_kind":"pith_short_16","alias_value":"GCLEV747KX77TVF2","created_at":"2026-07-05T05:34:07.670871+00:00"},{"alias_kind":"pith_short_8","alias_value":"GCLEV747","created_at":"2026-07-05T05:34:07.670871+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":50,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GCLEV747KX77TVF2YK5RSLY5AH","json":"https://pith.science/pith/GCLEV747KX77TVF2YK5RSLY5AH.json","graph_json":"https://pith.science/api/pith-number/GCLEV747KX77TVF2YK5RSLY5AH/graph.json","events_json":"https://pith.science/api/pith-number/GCLEV747KX77TVF2YK5RSLY5AH/events.json","paper":"https://pith.science/paper/GCLEV747"},"agent_actions":{"view_html":"https://pith.science/pith/GCLEV747KX77TVF2YK5RSLY5AH","download_json":"https://pith.science/pith/GCLEV747KX77TVF2YK5RSLY5AH.json","view_paper":"https://pith.science/paper/GCLEV747","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2301.07322&json=true","fetch_graph":"https://pith.science/api/pith-number/GCLEV747KX77TVF2YK5RSLY5AH/graph.json","fetch_events":"https://pith.science/api/pith-number/GCLEV747KX77TVF2YK5RSLY5AH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GCLEV747KX77TVF2YK5RSLY5AH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GCLEV747KX77TVF2YK5RSLY5AH/action/storage_attestation","attest_author":"https://pith.science/pith/GCLEV747KX77TVF2YK5RSLY5AH/action/author_attestation","sign_citation":"https://pith.science/pith/GCLEV747KX77TVF2YK5RSLY5AH/action/citation_signature","submit_replication":"https://pith.science/pith/GCLEV747KX77TVF2YK5RSLY5AH/action/replication_record"}},"created_at":"2026-07-05T05:34:07.670871+00:00","updated_at":"2026-07-05T05:34:07.670871+00:00"}