{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:NZMJBYVUNWZU4O3VUXLHHECFCI","short_pith_number":"pith:NZMJBYVU","schema_version":"1.0","canonical_sha256":"6e5890e2b46db34e3b75a5d673904512358314bff922a40097ece4ef250f176c","source":{"kind":"arxiv","id":"2509.01095","version":1},"attestation_state":"computed","paper":{"title":"An End-to-End Framework for Video Multi-Person Pose Estimation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Zhihong Wei","submitted_at":"2025-09-01T03:34:57Z","abstract_excerpt":"Video-based human pose estimation models aim to address scenarios that cannot be effectively solved by static image models such as motion blur, out-of-focus and occlusion. Most existing approaches consist of two stages: detecting human instances in each image frame and then using a temporal model for single-person pose estimation. This approach separates the spatial and temporal dimensions and cannot capture the global spatio-temporal context between spatial instances for end-to-end optimization. In addition, it relies on separate detectors and complex post-processing such as RoI cropping and "},"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":"2509.01095","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-09-01T03:34:57Z","cross_cats_sorted":[],"title_canon_sha256":"31dfd360a09db528a80d5d17ee4121f93c3611d962780978b0efe31e88d69bc3","abstract_canon_sha256":"15de0ed5dfac6d847da03134be36e1a60d40154b43d4f995e874d90f8253f844"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:02:53.542610Z","signature_b64":"ayFhSaYbfmlzpe1KRcRJPR4j1iPp+wUp4FLzvDD4/WXTYbCDvlB0ewGNRuZ0/mCyx/jLQ5wNi+nrO4mBe5yYDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6e5890e2b46db34e3b75a5d673904512358314bff922a40097ece4ef250f176c","last_reissued_at":"2026-07-05T12:02:53.542095Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:02:53.542095Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An End-to-End Framework for Video Multi-Person Pose Estimation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Zhihong Wei","submitted_at":"2025-09-01T03:34:57Z","abstract_excerpt":"Video-based human pose estimation models aim to address scenarios that cannot be effectively solved by static image models such as motion blur, out-of-focus and occlusion. Most existing approaches consist of two stages: detecting human instances in each image frame and then using a temporal model for single-person pose estimation. This approach separates the spatial and temporal dimensions and cannot capture the global spatio-temporal context between spatial instances for end-to-end optimization. In addition, it relies on separate detectors and complex post-processing such as RoI cropping and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.01095","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/2509.01095/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":"2509.01095","created_at":"2026-07-05T12:02:53.542152+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.01095v1","created_at":"2026-07-05T12:02:53.542152+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.01095","created_at":"2026-07-05T12:02:53.542152+00:00"},{"alias_kind":"pith_short_12","alias_value":"NZMJBYVUNWZU","created_at":"2026-07-05T12:02:53.542152+00:00"},{"alias_kind":"pith_short_16","alias_value":"NZMJBYVUNWZU4O3V","created_at":"2026-07-05T12:02:53.542152+00:00"},{"alias_kind":"pith_short_8","alias_value":"NZMJBYVU","created_at":"2026-07-05T12:02:53.542152+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/NZMJBYVUNWZU4O3VUXLHHECFCI","json":"https://pith.science/pith/NZMJBYVUNWZU4O3VUXLHHECFCI.json","graph_json":"https://pith.science/api/pith-number/NZMJBYVUNWZU4O3VUXLHHECFCI/graph.json","events_json":"https://pith.science/api/pith-number/NZMJBYVUNWZU4O3VUXLHHECFCI/events.json","paper":"https://pith.science/paper/NZMJBYVU"},"agent_actions":{"view_html":"https://pith.science/pith/NZMJBYVUNWZU4O3VUXLHHECFCI","download_json":"https://pith.science/pith/NZMJBYVUNWZU4O3VUXLHHECFCI.json","view_paper":"https://pith.science/paper/NZMJBYVU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.01095&json=true","fetch_graph":"https://pith.science/api/pith-number/NZMJBYVUNWZU4O3VUXLHHECFCI/graph.json","fetch_events":"https://pith.science/api/pith-number/NZMJBYVUNWZU4O3VUXLHHECFCI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NZMJBYVUNWZU4O3VUXLHHECFCI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NZMJBYVUNWZU4O3VUXLHHECFCI/action/storage_attestation","attest_author":"https://pith.science/pith/NZMJBYVUNWZU4O3VUXLHHECFCI/action/author_attestation","sign_citation":"https://pith.science/pith/NZMJBYVUNWZU4O3VUXLHHECFCI/action/citation_signature","submit_replication":"https://pith.science/pith/NZMJBYVUNWZU4O3VUXLHHECFCI/action/replication_record"}},"created_at":"2026-07-05T12:02:53.542152+00:00","updated_at":"2026-07-05T12:02:53.542152+00:00"}