{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:5KL2ICZLFS4YBRMJGPBO4FXJCW","short_pith_number":"pith:5KL2ICZL","schema_version":"1.0","canonical_sha256":"ea97a40b2b2cb980c58933c2ee16e915937b837dd097ee77be6fe0c649080292","source":{"kind":"arxiv","id":"2302.01825","version":2},"attestation_state":"computed","paper":{"title":"HDFormer: High-order Directed Transformer for 3D Human Pose Estimation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bin Luo, Hanbing Liu, Hanyuan Chen, Jun-Yan He, Wangmeng Xiang, Wei Liu, Xuansong Xie, Yifeng Geng, Zhi-Qi Cheng","submitted_at":"2023-02-03T16:00:48Z","abstract_excerpt":"Human pose estimation is a challenging task due to its structured data sequence nature. Existing methods primarily focus on pair-wise interaction of body joints, which is insufficient for scenarios involving overlapping joints and rapidly changing poses. To overcome these issues, we introduce a novel approach, the High-order Directed Transformer (HDFormer), which leverages high-order bone and joint relationships for improved pose estimation. Specifically, HDFormer incorporates both self-attention and high-order attention to formulate a multi-order attention module. This module facilitates firs"},"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":"2302.01825","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-02-03T16:00:48Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"47ba95a5bd7345d56ba97476602742fc01ab5e9b22d96a2a0a70719395254cf0","abstract_canon_sha256":"dabdd096bebe9fb73a13c2cdd1bbfd808ed48d83fc73ca1f3c7a11e6410aa060"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:11:59.932823Z","signature_b64":"4DwODMfoBXVz+lctpKBNi0LOSbyDt1r2wvJBF0Fkz6xZoKzhm5lvo7KBJCRfaEx0FtzIUcY+YBo1g9+xcZD4AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ea97a40b2b2cb980c58933c2ee16e915937b837dd097ee77be6fe0c649080292","last_reissued_at":"2026-07-05T06:11:59.932387Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:11:59.932387Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HDFormer: High-order Directed Transformer for 3D Human Pose Estimation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bin Luo, Hanbing Liu, Hanyuan Chen, Jun-Yan He, Wangmeng Xiang, Wei Liu, Xuansong Xie, Yifeng Geng, Zhi-Qi Cheng","submitted_at":"2023-02-03T16:00:48Z","abstract_excerpt":"Human pose estimation is a challenging task due to its structured data sequence nature. Existing methods primarily focus on pair-wise interaction of body joints, which is insufficient for scenarios involving overlapping joints and rapidly changing poses. To overcome these issues, we introduce a novel approach, the High-order Directed Transformer (HDFormer), which leverages high-order bone and joint relationships for improved pose estimation. Specifically, HDFormer incorporates both self-attention and high-order attention to formulate a multi-order attention module. This module facilitates firs"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.01825","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/2302.01825/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":"2302.01825","created_at":"2026-07-05T06:11:59.932444+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.01825v2","created_at":"2026-07-05T06:11:59.932444+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.01825","created_at":"2026-07-05T06:11:59.932444+00:00"},{"alias_kind":"pith_short_12","alias_value":"5KL2ICZLFS4Y","created_at":"2026-07-05T06:11:59.932444+00:00"},{"alias_kind":"pith_short_16","alias_value":"5KL2ICZLFS4YBRMJ","created_at":"2026-07-05T06:11:59.932444+00:00"},{"alias_kind":"pith_short_8","alias_value":"5KL2ICZL","created_at":"2026-07-05T06:11:59.932444+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.08806","citing_title":"L2A: Learning to Accumulate Pose History for Accurate 3D Human Pose Estimation","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08806","citing_title":"L2A: Learning to Accumulate Pose History for Accurate 3D Human Pose Estimation","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5KL2ICZLFS4YBRMJGPBO4FXJCW","json":"https://pith.science/pith/5KL2ICZLFS4YBRMJGPBO4FXJCW.json","graph_json":"https://pith.science/api/pith-number/5KL2ICZLFS4YBRMJGPBO4FXJCW/graph.json","events_json":"https://pith.science/api/pith-number/5KL2ICZLFS4YBRMJGPBO4FXJCW/events.json","paper":"https://pith.science/paper/5KL2ICZL"},"agent_actions":{"view_html":"https://pith.science/pith/5KL2ICZLFS4YBRMJGPBO4FXJCW","download_json":"https://pith.science/pith/5KL2ICZLFS4YBRMJGPBO4FXJCW.json","view_paper":"https://pith.science/paper/5KL2ICZL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.01825&json=true","fetch_graph":"https://pith.science/api/pith-number/5KL2ICZLFS4YBRMJGPBO4FXJCW/graph.json","fetch_events":"https://pith.science/api/pith-number/5KL2ICZLFS4YBRMJGPBO4FXJCW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5KL2ICZLFS4YBRMJGPBO4FXJCW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5KL2ICZLFS4YBRMJGPBO4FXJCW/action/storage_attestation","attest_author":"https://pith.science/pith/5KL2ICZLFS4YBRMJGPBO4FXJCW/action/author_attestation","sign_citation":"https://pith.science/pith/5KL2ICZLFS4YBRMJGPBO4FXJCW/action/citation_signature","submit_replication":"https://pith.science/pith/5KL2ICZLFS4YBRMJGPBO4FXJCW/action/replication_record"}},"created_at":"2026-07-05T06:11:59.932444+00:00","updated_at":"2026-07-05T06:11:59.932444+00:00"}