{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:YYPWEKUCSEGZRHQILEEPAQXQAG","short_pith_number":"pith:YYPWEKUC","schema_version":"1.0","canonical_sha256":"c61f622a82910d989e085908f042f001b8eee6e1e140a3a8516d9118d9efbac3","source":{"kind":"arxiv","id":"2604.09063","version":3},"attestation_state":"computed","paper":{"title":"Frequency-Enhanced Diffusion Models: Curriculum-Guided Semantic Alignment for Zero-Shot Skeleton Action Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Frequency-aware diffusion models recover fine-grained motion details for zero-shot skeleton action recognition.","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Jingyu Pan, Yuxi Zhou, Zhengbo Zhang, Zhigang Tu, Zhiyu Lin","submitted_at":"2026-04-10T07:42:47Z","abstract_excerpt":"Human action recognition is pivotal in computer vision, with applications ranging from surveillance to human-robot interaction. Despite the effectiveness of supervised skeleton-based methods, their reliance on exhaustive annotation limits generalization to novel actions. Zero-Shot Skeleton Action Recognition (ZSAR) emerges as a promising paradigm, yet it faces challenges due to the spectral bias of diffusion models, which oversmooth high-frequency dynamics. Here, we propose Frequency-Aware Diffusion for Skeleton-Text Matching (FDSM), integrating a Semantic-Guided Spectral Residual Module, a Ti"},"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":"2604.09063","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-04-10T07:42:47Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b1f8588feb8d159c38ec6254bdf39e7e91a8116c4aca5732d31ad2b7c784d861","abstract_canon_sha256":"1261fa2ca09e2716d7b799ac6f160c3645d934e2aa5dca469806d268579c4547"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T02:04:17.289592Z","signature_b64":"6SFHrN8fEOQD4h061R9kn7G5xJnAyNQ+naNnAmDbWWhkmQ+U9kzlcFPaY89fNmGRBSIHckTzZ20Zlp+t++o9Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c61f622a82910d989e085908f042f001b8eee6e1e140a3a8516d9118d9efbac3","last_reissued_at":"2026-06-02T02:04:17.289124Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T02:04:17.289124Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Frequency-Enhanced Diffusion Models: Curriculum-Guided Semantic Alignment for Zero-Shot Skeleton Action Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Frequency-aware diffusion models recover fine-grained motion details for zero-shot skeleton action recognition.","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Jingyu Pan, Yuxi Zhou, Zhengbo Zhang, Zhigang Tu, Zhiyu Lin","submitted_at":"2026-04-10T07:42:47Z","abstract_excerpt":"Human action recognition is pivotal in computer vision, with applications ranging from surveillance to human-robot interaction. Despite the effectiveness of supervised skeleton-based methods, their reliance on exhaustive annotation limits generalization to novel actions. Zero-Shot Skeleton Action Recognition (ZSAR) emerges as a promising paradigm, yet it faces challenges due to the spectral bias of diffusion models, which oversmooth high-frequency dynamics. Here, we propose Frequency-Aware Diffusion for Skeleton-Text Matching (FDSM), integrating a Semantic-Guided Spectral Residual Module, a Ti"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Our approach effectively recovers fine-grained motion details, achieving state-of-the-art performance on NTU RGB+D, PKU-MMD, and Kinetics-skeleton datasets.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the spectral bias of diffusion models is the primary bottleneck in zero-shot skeleton action recognition and that the three proposed modules (Semantic-Guided Spectral Residual Module, Timestep-Adaptive Spectral Loss, Curriculum-based Semantic Abstraction) directly correct it without introducing compensating errors or requiring dataset-specific tuning.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"FDSM recovers fine-grained motion details in zero-shot skeleton action recognition by integrating semantic-guided spectral residual, timestep-adaptive spectral loss, and curriculum-based semantic abstraction, reaching state-of-the-art on NTU RGB+D, PKU-MMD, and Kinetics-skeleton.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Frequency-aware diffusion models recover fine-grained motion details for zero-shot skeleton action recognition.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"fe89374dda37bff27fcd35277880ab25902691fdde3307236e58bbf2b68e06e4"},"source":{"id":"2604.09063","kind":"arxiv","version":3},"verdict":{"id":"44936811-1bfa-4b6f-9e5b-83b3fe7b60d1","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-10T16:51:09.040451Z","strongest_claim":"Our approach effectively recovers fine-grained motion details, achieving state-of-the-art performance on NTU RGB+D, PKU-MMD, and Kinetics-skeleton datasets.","one_line_summary":"FDSM recovers fine-grained motion details in zero-shot skeleton action recognition by integrating semantic-guided spectral residual, timestep-adaptive spectral loss, and curriculum-based semantic abstraction, reaching state-of-the-art on NTU RGB+D, PKU-MMD, and Kinetics-skeleton.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the spectral bias of diffusion models is the primary bottleneck in zero-shot skeleton action recognition and that the three proposed modules (Semantic-Guided Spectral Residual Module, Timestep-Adaptive Spectral Loss, Curriculum-based Semantic Abstraction) directly correct it without introducing compensating errors or requiring dataset-specific tuning.","pith_extraction_headline":"Frequency-aware diffusion models recover fine-grained motion details for zero-shot skeleton action recognition."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.09063/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":"2604.09063","created_at":"2026-06-02T02:04:17.289189+00:00"},{"alias_kind":"arxiv_version","alias_value":"2604.09063v3","created_at":"2026-06-02T02:04:17.289189+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.09063","created_at":"2026-06-02T02:04:17.289189+00:00"},{"alias_kind":"pith_short_12","alias_value":"YYPWEKUCSEGZ","created_at":"2026-06-02T02:04:17.289189+00:00"},{"alias_kind":"pith_short_16","alias_value":"YYPWEKUCSEGZRHQI","created_at":"2026-06-02T02:04:17.289189+00:00"},{"alias_kind":"pith_short_8","alias_value":"YYPWEKUC","created_at":"2026-06-02T02:04:17.289189+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/YYPWEKUCSEGZRHQILEEPAQXQAG","json":"https://pith.science/pith/YYPWEKUCSEGZRHQILEEPAQXQAG.json","graph_json":"https://pith.science/api/pith-number/YYPWEKUCSEGZRHQILEEPAQXQAG/graph.json","events_json":"https://pith.science/api/pith-number/YYPWEKUCSEGZRHQILEEPAQXQAG/events.json","paper":"https://pith.science/paper/YYPWEKUC"},"agent_actions":{"view_html":"https://pith.science/pith/YYPWEKUCSEGZRHQILEEPAQXQAG","download_json":"https://pith.science/pith/YYPWEKUCSEGZRHQILEEPAQXQAG.json","view_paper":"https://pith.science/paper/YYPWEKUC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2604.09063&json=true","fetch_graph":"https://pith.science/api/pith-number/YYPWEKUCSEGZRHQILEEPAQXQAG/graph.json","fetch_events":"https://pith.science/api/pith-number/YYPWEKUCSEGZRHQILEEPAQXQAG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YYPWEKUCSEGZRHQILEEPAQXQAG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YYPWEKUCSEGZRHQILEEPAQXQAG/action/storage_attestation","attest_author":"https://pith.science/pith/YYPWEKUCSEGZRHQILEEPAQXQAG/action/author_attestation","sign_citation":"https://pith.science/pith/YYPWEKUCSEGZRHQILEEPAQXQAG/action/citation_signature","submit_replication":"https://pith.science/pith/YYPWEKUCSEGZRHQILEEPAQXQAG/action/replication_record"}},"created_at":"2026-06-02T02:04:17.289189+00:00","updated_at":"2026-06-02T02:04:17.289189+00:00"}