{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:SDS2772YTVK32D34BLYITNG3Q2","short_pith_number":"pith:SDS2772Y","schema_version":"1.0","canonical_sha256":"90e5afff589d55bd0f7c0af089b4db8695ef34979e53a0c0ffa4346d0e6029c9","source":{"kind":"arxiv","id":"2501.09502","version":1},"attestation_state":"computed","paper":{"title":"Omni-Emotion: Extending Video MLLM with Detailed Face and Audio Modeling for Multimodal Emotion Analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Detao Bai, Qize Yang, Xihan Wei, Yi-Xing Peng","submitted_at":"2025-01-16T12:27:05Z","abstract_excerpt":"Understanding emotions accurately is essential for fields like human-computer interaction. Due to the complexity of emotions and their multi-modal nature (e.g., emotions are influenced by facial expressions and audio), researchers have turned to using multi-modal models to understand human emotions rather than single-modality. However, current video multi-modal large language models (MLLMs) encounter difficulties in effectively integrating audio and identifying subtle facial micro-expressions. Furthermore, the lack of detailed emotion analysis datasets also limits the development of multimodal"},"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":"2501.09502","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-16T12:27:05Z","cross_cats_sorted":[],"title_canon_sha256":"4d802a483b6537adef11273a1358992bfe8f40b74d84b77ac6bfff7dce033a61","abstract_canon_sha256":"69212df531ba0fc810106875d0177ca4261796a0cfcbd715b0142cfcfc132264"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:01:47.973233Z","signature_b64":"pLd9hGVVMrb3Ce646RuJzir6OA9WMMdfRCh9wd3PsJH3t+q2HFxvcQEHEvlyv2Wj5x2qtxtarK9nAfEd2zGSAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"90e5afff589d55bd0f7c0af089b4db8695ef34979e53a0c0ffa4346d0e6029c9","last_reissued_at":"2026-07-05T10:01:47.972753Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:01:47.972753Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Omni-Emotion: Extending Video MLLM with Detailed Face and Audio Modeling for Multimodal Emotion Analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Detao Bai, Qize Yang, Xihan Wei, Yi-Xing Peng","submitted_at":"2025-01-16T12:27:05Z","abstract_excerpt":"Understanding emotions accurately is essential for fields like human-computer interaction. Due to the complexity of emotions and their multi-modal nature (e.g., emotions are influenced by facial expressions and audio), researchers have turned to using multi-modal models to understand human emotions rather than single-modality. However, current video multi-modal large language models (MLLMs) encounter difficulties in effectively integrating audio and identifying subtle facial micro-expressions. Furthermore, the lack of detailed emotion analysis datasets also limits the development of multimodal"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.09502","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/2501.09502/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":"2501.09502","created_at":"2026-07-05T10:01:47.972812+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.09502v1","created_at":"2026-07-05T10:01:47.972812+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.09502","created_at":"2026-07-05T10:01:47.972812+00:00"},{"alias_kind":"pith_short_12","alias_value":"SDS2772YTVK3","created_at":"2026-07-05T10:01:47.972812+00:00"},{"alias_kind":"pith_short_16","alias_value":"SDS2772YTVK32D34","created_at":"2026-07-05T10:01:47.972812+00:00"},{"alias_kind":"pith_short_8","alias_value":"SDS2772Y","created_at":"2026-07-05T10:01:47.972812+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25325","citing_title":"Omni-Perception Policy Optimization for Multimodal Emotion Reasoning","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07585","citing_title":"Multimodal Group Emotion Recognition In-the-Wild Towards a Privacy-Safe Non-Individual Approach","ref_index":242,"is_internal_anchor":false},{"citing_arxiv_id":"2603.02123","citing_title":"Nano-EmoX: Unifying Multimodal Emotional Intelligence from Perception to Empathy","ref_index":63,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08209","citing_title":"OmniJigsaw: Enhancing Omni-Modal Reasoning via Modality-Orchestrated Reordering","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15823","citing_title":"Watching Movies Like a Human: Egocentric Emotion Understanding for Embodied Companions","ref_index":54,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SDS2772YTVK32D34BLYITNG3Q2","json":"https://pith.science/pith/SDS2772YTVK32D34BLYITNG3Q2.json","graph_json":"https://pith.science/api/pith-number/SDS2772YTVK32D34BLYITNG3Q2/graph.json","events_json":"https://pith.science/api/pith-number/SDS2772YTVK32D34BLYITNG3Q2/events.json","paper":"https://pith.science/paper/SDS2772Y"},"agent_actions":{"view_html":"https://pith.science/pith/SDS2772YTVK32D34BLYITNG3Q2","download_json":"https://pith.science/pith/SDS2772YTVK32D34BLYITNG3Q2.json","view_paper":"https://pith.science/paper/SDS2772Y","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.09502&json=true","fetch_graph":"https://pith.science/api/pith-number/SDS2772YTVK32D34BLYITNG3Q2/graph.json","fetch_events":"https://pith.science/api/pith-number/SDS2772YTVK32D34BLYITNG3Q2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SDS2772YTVK32D34BLYITNG3Q2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SDS2772YTVK32D34BLYITNG3Q2/action/storage_attestation","attest_author":"https://pith.science/pith/SDS2772YTVK32D34BLYITNG3Q2/action/author_attestation","sign_citation":"https://pith.science/pith/SDS2772YTVK32D34BLYITNG3Q2/action/citation_signature","submit_replication":"https://pith.science/pith/SDS2772YTVK32D34BLYITNG3Q2/action/replication_record"}},"created_at":"2026-07-05T10:01:47.972812+00:00","updated_at":"2026-07-05T10:01:47.972812+00:00"}