{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:SS2WSQT72QR5ZIKUGPOXLJX2SB","short_pith_number":"pith:SS2WSQT7","schema_version":"1.0","canonical_sha256":"94b569427fd423dca15433dd75a6fa906e35fd0404dd91237bf4367ffc93c67c","source":{"kind":"arxiv","id":"2511.05611","version":2},"attestation_state":"computed","paper":{"title":"Focus on What Matters: Constraining Spatial-Temporal Attention via Action-Units for Noise-Resilient AQA","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chen Sun, Shuaikang Zhu, Yang Yang, Yiding Sun, Zihao Guo","submitted_at":"2025-11-06T13:00:22Z","abstract_excerpt":"The core challenge in Action Quality Assessment (AQA) lies in extracting fine-grained motion features from redundant and complex video backgrounds. Existing global feature learning methods are constrained by extremely low \"signal-to-noise ratios\", making it difficult to distinguish intrinsic actions from background clutter. To address this, we propose a Pose-Guided Intrinsic Motion Distillation Framework that explicitly enforces physical constraints to focus on motion subjects and decouple motion execution from environmental outcomes. First, we design an Action-Unit Parser that constructs dyna"},"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":"2511.05611","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-11-06T13:00:22Z","cross_cats_sorted":[],"title_canon_sha256":"ab1af7442e5cd7b36dd84614ac7122934d79234bd38ee8bd0baf473f96cb9d09","abstract_canon_sha256":"ae59c9968b4d18ce59e63dea704bf8171a614074a2e7769b0a378289657dfd7b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-24T01:23:01.288748Z","signature_b64":"cnk4bhV+6GzKDOgSA+sc9DrY4kKMgv76E0oW8I+pHyRmWiCDKXURCOkyVexE3/X8c78c+osobrahvOaT/0ySCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"94b569427fd423dca15433dd75a6fa906e35fd0404dd91237bf4367ffc93c67c","last_reissued_at":"2026-07-24T01:23:01.287843Z","signature_status":"signed_v1","first_computed_at":"2026-07-24T01:23:01.287843Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Focus on What Matters: Constraining Spatial-Temporal Attention via Action-Units for Noise-Resilient AQA","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chen Sun, Shuaikang Zhu, Yang Yang, Yiding Sun, Zihao Guo","submitted_at":"2025-11-06T13:00:22Z","abstract_excerpt":"The core challenge in Action Quality Assessment (AQA) lies in extracting fine-grained motion features from redundant and complex video backgrounds. Existing global feature learning methods are constrained by extremely low \"signal-to-noise ratios\", making it difficult to distinguish intrinsic actions from background clutter. To address this, we propose a Pose-Guided Intrinsic Motion Distillation Framework that explicitly enforces physical constraints to focus on motion subjects and decouple motion execution from environmental outcomes. First, we design an Action-Unit Parser that constructs dyna"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2511.05611","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/2511.05611/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":"2511.05611","created_at":"2026-07-24T01:23:01.288253+00:00"},{"alias_kind":"arxiv_version","alias_value":"2511.05611v2","created_at":"2026-07-24T01:23:01.288253+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2511.05611","created_at":"2026-07-24T01:23:01.288253+00:00"},{"alias_kind":"pith_short_12","alias_value":"SS2WSQT72QR5","created_at":"2026-07-24T01:23:01.288253+00:00"},{"alias_kind":"pith_short_16","alias_value":"SS2WSQT72QR5ZIKU","created_at":"2026-07-24T01:23:01.288253+00:00"},{"alias_kind":"pith_short_8","alias_value":"SS2WSQT7","created_at":"2026-07-24T01:23:01.288253+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2606.29230","citing_title":"Again-Pose: Anchor-Guided Adaptive Inter-Frame Motion Cues Propagating for High-quality Human Pose Reconstruction","ref_index":46,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SS2WSQT72QR5ZIKUGPOXLJX2SB","json":"https://pith.science/pith/SS2WSQT72QR5ZIKUGPOXLJX2SB.json","graph_json":"https://pith.science/api/pith-number/SS2WSQT72QR5ZIKUGPOXLJX2SB/graph.json","events_json":"https://pith.science/api/pith-number/SS2WSQT72QR5ZIKUGPOXLJX2SB/events.json","paper":"https://pith.science/paper/SS2WSQT7"},"agent_actions":{"view_html":"https://pith.science/pith/SS2WSQT72QR5ZIKUGPOXLJX2SB","download_json":"https://pith.science/pith/SS2WSQT72QR5ZIKUGPOXLJX2SB.json","view_paper":"https://pith.science/paper/SS2WSQT7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2511.05611&json=true","fetch_graph":"https://pith.science/api/pith-number/SS2WSQT72QR5ZIKUGPOXLJX2SB/graph.json","fetch_events":"https://pith.science/api/pith-number/SS2WSQT72QR5ZIKUGPOXLJX2SB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SS2WSQT72QR5ZIKUGPOXLJX2SB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SS2WSQT72QR5ZIKUGPOXLJX2SB/action/storage_attestation","attest_author":"https://pith.science/pith/SS2WSQT72QR5ZIKUGPOXLJX2SB/action/author_attestation","sign_citation":"https://pith.science/pith/SS2WSQT72QR5ZIKUGPOXLJX2SB/action/citation_signature","submit_replication":"https://pith.science/pith/SS2WSQT72QR5ZIKUGPOXLJX2SB/action/replication_record"}},"created_at":"2026-07-24T01:23:01.288253+00:00","updated_at":"2026-07-24T01:23:01.288253+00:00"}