{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:M362KP5LHBM65DAHDDVX7ZCV46","short_pith_number":"pith:M362KP5L","schema_version":"1.0","canonical_sha256":"66fda53fab3859ee8c0718eb7fe455e790f45d67c9e5d612955d014694808561","source":{"kind":"arxiv","id":"2501.15111","version":1},"attestation_state":"computed","paper":{"title":"HumanOmni: A Large Vision-Speech Language Model for Human-Centric Video Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Boyuan Sun, Detao Bai, Jiaxing Zhao, Liefeng Bo, Qize Yang, Shenghao Fu, Shimin Yao, Weixuan Chen, Xiang Chen, Xihan Wei, Yixing Peng","submitted_at":"2025-01-25T07:26:37Z","abstract_excerpt":"In human-centric scenes, the ability to simultaneously understand visual and auditory information is crucial. While recent omni models can process multiple modalities, they generally lack effectiveness in human-centric scenes due to the absence of large-scale, specialized datasets and non-targeted architectures. In this work, we developed HumanOmni, the industry's first human-centric Omni-multimodal large language model. We constructed a dataset containing over 2.4 million human-centric video clips with detailed captions and more than 14 million instructions, facilitating the understanding of "},"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":"2501.15111","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-25T07:26:37Z","cross_cats_sorted":[],"title_canon_sha256":"3ea99b694cae0e6d4885a13829950295c6f08ef6ff43b6316e28247dc1d5184a","abstract_canon_sha256":"8c1e739e6cf77b7687c121441484abab7b9516ef4add91df0e4c1951995e19a7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:05:24.596562Z","signature_b64":"Qrflf0u/CqEX/9mYsh7c23LiMfAQEIttQzrQ0jIEX7PEcVEdgl2fA508N3Gu9/Zx/6g604+oEFMoNBl9/QUvCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"66fda53fab3859ee8c0718eb7fe455e790f45d67c9e5d612955d014694808561","last_reissued_at":"2026-07-05T10:05:24.595994Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:05:24.595994Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HumanOmni: A Large Vision-Speech Language Model for Human-Centric Video Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Boyuan Sun, Detao Bai, Jiaxing Zhao, Liefeng Bo, Qize Yang, Shenghao Fu, Shimin Yao, Weixuan Chen, Xiang Chen, Xihan Wei, Yixing Peng","submitted_at":"2025-01-25T07:26:37Z","abstract_excerpt":"In human-centric scenes, the ability to simultaneously understand visual and auditory information is crucial. While recent omni models can process multiple modalities, they generally lack effectiveness in human-centric scenes due to the absence of large-scale, specialized datasets and non-targeted architectures. In this work, we developed HumanOmni, the industry's first human-centric Omni-multimodal large language model. We constructed a dataset containing over 2.4 million human-centric video clips with detailed captions and more than 14 million instructions, facilitating the understanding of "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.15111","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/2501.15111/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":"2501.15111","created_at":"2026-07-05T10:05:24.596056+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.15111v1","created_at":"2026-07-05T10:05:24.596056+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.15111","created_at":"2026-07-05T10:05:24.596056+00:00"},{"alias_kind":"pith_short_12","alias_value":"M362KP5LHBM6","created_at":"2026-07-05T10:05:24.596056+00:00"},{"alias_kind":"pith_short_16","alias_value":"M362KP5LHBM65DAH","created_at":"2026-07-05T10:05:24.596056+00:00"},{"alias_kind":"pith_short_8","alias_value":"M362KP5L","created_at":"2026-07-05T10:05:24.596056+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":18,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25325","citing_title":"Omni-Perception Policy Optimization for Multimodal Emotion Reasoning","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2606.24286","citing_title":"AVOC: Enhancing Hour-Level Audio-Video Understanding in Omni-Modal LLMs via Retrieval-Inspired Token Compression","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2606.20970","citing_title":"CogniRoute: Learning to Route Social Evidence in Omni-Modal Models","ref_index":93,"is_internal_anchor":false},{"citing_arxiv_id":"2606.05896","citing_title":"Resonant Minds: Closed-Loop Social Avatars with Theory of Mind","ref_index":52,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07643","citing_title":"AVI-Bench: Toward Human-like Audio-Visual Intelligence of Omni-MLLMs","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21417","citing_title":"Ordering Matters: Rank-Aware Selective Fusion for Blended Emotion Recognition","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2508.10016","citing_title":"Training-Free Multimodal Large Language Model Orchestration","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2501.05067","citing_title":"LLaVA-Octopus: Unlocking Instruction-Driven Adaptive Projector Fusion for Video Understanding","ref_index":94,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21417","citing_title":"Ordering Matters: Rank-Aware Selective Fusion for Blended Emotion Recognition","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15764","citing_title":"GRASP: Learning to Ground Social Reasoning in Multi-Person Non-Verbal Interactions","ref_index":91,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18018","citing_title":"See What I Mean: Aligning Vision and Language Representations for Video Fine-grained Object Understanding","ref_index":109,"is_internal_anchor":false},{"citing_arxiv_id":"2508.10016","citing_title":"Training-Free Multimodal Large Language Model Orchestration","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2604.00013","citing_title":"C2F-Thinker: Coarse-to-Fine Reasoning with Hint-Guided Reinforcement Learning for Multimodal Sentiment Analysis","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18460","citing_title":"Learning Invariant Modality Representation for Robust Multimodal Learning from a Causal Inference Perspective","ref_index":283,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07593","citing_title":"TraceAV-Bench: Benchmarking Multi-Hop Trajectory Reasoning over Long Audio-Visual Videos","ref_index":13,"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":60,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16617","citing_title":"AVRT: Audio-Visual Reasoning Transfer through Single-Modality Teachers","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15823","citing_title":"Watching Movies Like a Human: Egocentric Emotion Understanding for Embodied Companions","ref_index":56,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/M362KP5LHBM65DAHDDVX7ZCV46","json":"https://pith.science/pith/M362KP5LHBM65DAHDDVX7ZCV46.json","graph_json":"https://pith.science/api/pith-number/M362KP5LHBM65DAHDDVX7ZCV46/graph.json","events_json":"https://pith.science/api/pith-number/M362KP5LHBM65DAHDDVX7ZCV46/events.json","paper":"https://pith.science/paper/M362KP5L"},"agent_actions":{"view_html":"https://pith.science/pith/M362KP5LHBM65DAHDDVX7ZCV46","download_json":"https://pith.science/pith/M362KP5LHBM65DAHDDVX7ZCV46.json","view_paper":"https://pith.science/paper/M362KP5L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.15111&json=true","fetch_graph":"https://pith.science/api/pith-number/M362KP5LHBM65DAHDDVX7ZCV46/graph.json","fetch_events":"https://pith.science/api/pith-number/M362KP5LHBM65DAHDDVX7ZCV46/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M362KP5LHBM65DAHDDVX7ZCV46/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M362KP5LHBM65DAHDDVX7ZCV46/action/storage_attestation","attest_author":"https://pith.science/pith/M362KP5LHBM65DAHDDVX7ZCV46/action/author_attestation","sign_citation":"https://pith.science/pith/M362KP5LHBM65DAHDDVX7ZCV46/action/citation_signature","submit_replication":"https://pith.science/pith/M362KP5LHBM65DAHDDVX7ZCV46/action/replication_record"}},"created_at":"2026-07-05T10:05:24.596056+00:00","updated_at":"2026-07-05T10:05:24.596056+00:00"}