{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:3XJBEESSWTKPH6NUYFJLQWDNCD","short_pith_number":"pith:3XJBEESS","schema_version":"1.0","canonical_sha256":"ddd2121252b4d4f3f9b4c152b8586d10de6863eb93a27eb9bc1150aac7a202d2","source":{"kind":"arxiv","id":"2504.18152","version":1},"attestation_state":"computed","paper":{"title":"ActionArt: Advancing Multimodal Large Models for Fine-Grained Human-Centric Video Understanding","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kun-Yu Lin, Qize Yang, Shenghao Fu, Wei-Shi Zheng, Xihan Wei, Yi-Xing Peng, Yu-Ming Tang","submitted_at":"2025-04-25T08:05:32Z","abstract_excerpt":"Fine-grained understanding of human actions and poses in videos is essential for human-centric AI applications. In this work, we introduce ActionArt, a fine-grained video-caption dataset designed to advance research in human-centric multimodal understanding. Our dataset comprises thousands of videos capturing a broad spectrum of human actions, human-object interactions, and diverse scenarios, each accompanied by detailed annotations that meticulously label every limb movement. We develop eight sub-tasks to evaluate the fine-grained understanding capabilities of existing large multimodal models"},"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":"2504.18152","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-25T08:05:32Z","cross_cats_sorted":[],"title_canon_sha256":"155b70e552149a47e3c60786f9d30dd76f3df8b86400b1dc2e6c8abf73a9c679","abstract_canon_sha256":"1b913c97280235fcf7bd3a21acad7fd5c8c8aff1cac8164e3944cda47f00ef12"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:54:02.806284Z","signature_b64":"8/Y6coE4NYM51fjVQmXDipWhnwNB8qij/WKszIrA2t06mVG6Z4DRHfmMYzUenrWimgPlAlPdLtJRIC0w4z+fDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ddd2121252b4d4f3f9b4c152b8586d10de6863eb93a27eb9bc1150aac7a202d2","last_reissued_at":"2026-07-05T10:54:02.805840Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:54:02.805840Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ActionArt: Advancing Multimodal Large Models for Fine-Grained Human-Centric Video Understanding","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kun-Yu Lin, Qize Yang, Shenghao Fu, Wei-Shi Zheng, Xihan Wei, Yi-Xing Peng, Yu-Ming Tang","submitted_at":"2025-04-25T08:05:32Z","abstract_excerpt":"Fine-grained understanding of human actions and poses in videos is essential for human-centric AI applications. In this work, we introduce ActionArt, a fine-grained video-caption dataset designed to advance research in human-centric multimodal understanding. Our dataset comprises thousands of videos capturing a broad spectrum of human actions, human-object interactions, and diverse scenarios, each accompanied by detailed annotations that meticulously label every limb movement. We develop eight sub-tasks to evaluate the fine-grained understanding capabilities of existing large multimodal models"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.18152","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/2504.18152/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":"2504.18152","created_at":"2026-07-05T10:54:02.805893+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.18152v1","created_at":"2026-07-05T10:54:02.805893+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.18152","created_at":"2026-07-05T10:54:02.805893+00:00"},{"alias_kind":"pith_short_12","alias_value":"3XJBEESSWTKP","created_at":"2026-07-05T10:54:02.805893+00:00"},{"alias_kind":"pith_short_16","alias_value":"3XJBEESSWTKPH6NU","created_at":"2026-07-05T10:54:02.805893+00:00"},{"alias_kind":"pith_short_8","alias_value":"3XJBEESS","created_at":"2026-07-05T10:54:02.805893+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.27999","citing_title":"HumanMoveVQA: Can Video MLLMs reason about human movement in videos?","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2606.27999","citing_title":"HumanMoveVQA: Can Video MLLMs reason about human movement in videos?","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.28604","citing_title":"Mining Multi-Modality Spatio-Temporal Cues for Video Important Person Identification","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05079","citing_title":"SVAgent: Storyline-Guided Long Video Understanding via Cross-Modal Multi-Agent Collaboration","ref_index":29,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3XJBEESSWTKPH6NUYFJLQWDNCD","json":"https://pith.science/pith/3XJBEESSWTKPH6NUYFJLQWDNCD.json","graph_json":"https://pith.science/api/pith-number/3XJBEESSWTKPH6NUYFJLQWDNCD/graph.json","events_json":"https://pith.science/api/pith-number/3XJBEESSWTKPH6NUYFJLQWDNCD/events.json","paper":"https://pith.science/paper/3XJBEESS"},"agent_actions":{"view_html":"https://pith.science/pith/3XJBEESSWTKPH6NUYFJLQWDNCD","download_json":"https://pith.science/pith/3XJBEESSWTKPH6NUYFJLQWDNCD.json","view_paper":"https://pith.science/paper/3XJBEESS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.18152&json=true","fetch_graph":"https://pith.science/api/pith-number/3XJBEESSWTKPH6NUYFJLQWDNCD/graph.json","fetch_events":"https://pith.science/api/pith-number/3XJBEESSWTKPH6NUYFJLQWDNCD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3XJBEESSWTKPH6NUYFJLQWDNCD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3XJBEESSWTKPH6NUYFJLQWDNCD/action/storage_attestation","attest_author":"https://pith.science/pith/3XJBEESSWTKPH6NUYFJLQWDNCD/action/author_attestation","sign_citation":"https://pith.science/pith/3XJBEESSWTKPH6NUYFJLQWDNCD/action/citation_signature","submit_replication":"https://pith.science/pith/3XJBEESSWTKPH6NUYFJLQWDNCD/action/replication_record"}},"created_at":"2026-07-05T10:54:02.805893+00:00","updated_at":"2026-07-05T10:54:02.805893+00:00"}