{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:FAZ3VK6ZU3SBDDR2BQA5VWAJIP","short_pith_number":"pith:FAZ3VK6Z","schema_version":"1.0","canonical_sha256":"2833baabd9a6e4118e3a0c01dad80943fac7286ea66e60ea210792f6aeb4fea9","source":{"kind":"arxiv","id":"2507.08344","version":2},"attestation_state":"computed","paper":{"title":"MM-Gesture: Towards Precise Micro-Gesture Recognition through Multimodal Fusion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dan Guo, Fei Wang, Jihao Gu, Kun Li, Yanyan Wei, Zhiliang Wu","submitted_at":"2025-07-11T06:45:42Z","abstract_excerpt":"In this paper, we present MM-Gesture, the solution developed by our team HFUT-VUT, which ranked 1st in the micro-gesture classification track of the 3rd MiGA Challenge at IJCAI 2025, achieving superior performance compared to previous state-of-the-art methods. MM-Gesture is a multimodal fusion framework designed specifically for recognizing subtle and short-duration micro-gestures (MGs), integrating complementary cues from joint, limb, RGB video, Taylor-series video, optical-flow video, and depth video modalities. Utilizing PoseConv3D and Video Swin Transformer architectures with a novel modal"},"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":"2507.08344","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-11T06:45:42Z","cross_cats_sorted":[],"title_canon_sha256":"2d8e2c4f6dd90b9bc8dcf94ed16055f43bad7318319fb018427c2b166b7661b5","abstract_canon_sha256":"22b2641bfd72841de1ff0e7988d33d9386fe04b7a4f88b6299552780b309bc18"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:48:27.147779Z","signature_b64":"F1NsEhEP/2oMFhdIQdjBHcC1fcGIWikp32Bpq9u+Qb0GdZXA/X5F825mmAv4u7eh5bm5vyXAQnNvBSqcM6f7Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2833baabd9a6e4118e3a0c01dad80943fac7286ea66e60ea210792f6aeb4fea9","last_reissued_at":"2026-07-05T11:48:27.147279Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:48:27.147279Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MM-Gesture: Towards Precise Micro-Gesture Recognition through Multimodal Fusion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dan Guo, Fei Wang, Jihao Gu, Kun Li, Yanyan Wei, Zhiliang Wu","submitted_at":"2025-07-11T06:45:42Z","abstract_excerpt":"In this paper, we present MM-Gesture, the solution developed by our team HFUT-VUT, which ranked 1st in the micro-gesture classification track of the 3rd MiGA Challenge at IJCAI 2025, achieving superior performance compared to previous state-of-the-art methods. MM-Gesture is a multimodal fusion framework designed specifically for recognizing subtle and short-duration micro-gestures (MGs), integrating complementary cues from joint, limb, RGB video, Taylor-series video, optical-flow video, and depth video modalities. Utilizing PoseConv3D and Video Swin Transformer architectures with a novel modal"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.08344","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/2507.08344/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":"2507.08344","created_at":"2026-07-05T11:48:27.147341+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.08344v2","created_at":"2026-07-05T11:48:27.147341+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.08344","created_at":"2026-07-05T11:48:27.147341+00:00"},{"alias_kind":"pith_short_12","alias_value":"FAZ3VK6ZU3SB","created_at":"2026-07-05T11:48:27.147341+00:00"},{"alias_kind":"pith_short_16","alias_value":"FAZ3VK6ZU3SBDDR2","created_at":"2026-07-05T11:48:27.147341+00:00"},{"alias_kind":"pith_short_8","alias_value":"FAZ3VK6Z","created_at":"2026-07-05T11:48:27.147341+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.13030","citing_title":"A Multi-Modal Framework with Cross-Subject Pseudo-Labeling and Semantic Alignment for Micro-Gesture Recognition","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2606.11645","citing_title":"Motion Reinforces Appearance: RGB-Skeleton Gated Residual Fusion for Micro-Gesture Online Recognition","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2606.09261","citing_title":"Self-supervised Learning Matters: A Simple Ensemble Solution for Micro-Gesture Recognition","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07355","citing_title":"Spatial-Temporal Decoupled Adapter for Micro-gesture Online Recognition","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31249","citing_title":"Rethinking the Role of Feature Engineering and Learning Strategies in Few-Shot Hidden Emotion Recognition","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17179","citing_title":"iMiGUE-3K: A Large-Scale Benchmark for Micro-Gesture Analysis with Self-Supervised Learning","ref_index":96,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21011","citing_title":"Micro-DualNet: Dual-Path Spatio-Temporal Network for Micro-Action Recognition","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FAZ3VK6ZU3SBDDR2BQA5VWAJIP","json":"https://pith.science/pith/FAZ3VK6ZU3SBDDR2BQA5VWAJIP.json","graph_json":"https://pith.science/api/pith-number/FAZ3VK6ZU3SBDDR2BQA5VWAJIP/graph.json","events_json":"https://pith.science/api/pith-number/FAZ3VK6ZU3SBDDR2BQA5VWAJIP/events.json","paper":"https://pith.science/paper/FAZ3VK6Z"},"agent_actions":{"view_html":"https://pith.science/pith/FAZ3VK6ZU3SBDDR2BQA5VWAJIP","download_json":"https://pith.science/pith/FAZ3VK6ZU3SBDDR2BQA5VWAJIP.json","view_paper":"https://pith.science/paper/FAZ3VK6Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.08344&json=true","fetch_graph":"https://pith.science/api/pith-number/FAZ3VK6ZU3SBDDR2BQA5VWAJIP/graph.json","fetch_events":"https://pith.science/api/pith-number/FAZ3VK6ZU3SBDDR2BQA5VWAJIP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FAZ3VK6ZU3SBDDR2BQA5VWAJIP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FAZ3VK6ZU3SBDDR2BQA5VWAJIP/action/storage_attestation","attest_author":"https://pith.science/pith/FAZ3VK6ZU3SBDDR2BQA5VWAJIP/action/author_attestation","sign_citation":"https://pith.science/pith/FAZ3VK6ZU3SBDDR2BQA5VWAJIP/action/citation_signature","submit_replication":"https://pith.science/pith/FAZ3VK6ZU3SBDDR2BQA5VWAJIP/action/replication_record"}},"created_at":"2026-07-05T11:48:27.147341+00:00","updated_at":"2026-07-05T11:48:27.147341+00:00"}