{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DY3CHACHXNKKQNEJL2SFHETNKJ","short_pith_number":"pith:DY3CHACH","schema_version":"1.0","canonical_sha256":"1e36238047bb54a834895ea453926d5272111eb7cb182945667b2361c34572fc","source":{"kind":"arxiv","id":"2410.01495","version":3},"attestation_state":"computed","paper":{"title":"OV-MER: Towards Open-Vocabulary Multimodal Emotion Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.HC","authors_text":"Bin Liu, Hailiang Yao, Haiyang Sun, Hao Gu, Haoyu Chen, Jiangyan Yi, Jianhua Tao, Lan Chen, Licai Sun, Rui Liu, Shan Liang, Shun Chen, Siyuan Zhang, Ya Li, Zheng Lian, Zhuofan Wen","submitted_at":"2024-10-02T12:45:09Z","abstract_excerpt":"Multimodal Emotion Recognition (MER) is a critical research area that seeks to decode human emotions from diverse data modalities. However, existing machine learning methods predominantly rely on predefined emotion taxonomies, which fail to capture the inherent complexity, subtlety, and multi-appraisal nature of human emotional experiences, as demonstrated by studies in psychology and cognitive science. To overcome this limitation, we advocate for introducing the concept of open vocabulary into MER. This paradigm shift aims to enable models to predict emotions beyond a fixed label space, accom"},"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":"2410.01495","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.HC","submitted_at":"2024-10-02T12:45:09Z","cross_cats_sorted":[],"title_canon_sha256":"a85c84dae8859d623dda64783db5599860dd80f949410ea4fd2cf635a4b1c68b","abstract_canon_sha256":"e0cc9d06829d1d8fccd4e40614496bc2f67b6c2d97ece570588bf229af15f3f1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:59:47.822546Z","signature_b64":"7Hr59zEYCDS9MjVnr/dDl5XtaBn8Q0awqUh+3IdhSFrE6fvty+I4OKUAL4x9ig+2TPiKKzIsEXj3GDudjcyJBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1e36238047bb54a834895ea453926d5272111eb7cb182945667b2361c34572fc","last_reissued_at":"2026-07-05T10:59:47.822038Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:59:47.822038Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OV-MER: Towards Open-Vocabulary Multimodal Emotion Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.HC","authors_text":"Bin Liu, Hailiang Yao, Haiyang Sun, Hao Gu, Haoyu Chen, Jiangyan Yi, Jianhua Tao, Lan Chen, Licai Sun, Rui Liu, Shan Liang, Shun Chen, Siyuan Zhang, Ya Li, Zheng Lian, Zhuofan Wen","submitted_at":"2024-10-02T12:45:09Z","abstract_excerpt":"Multimodal Emotion Recognition (MER) is a critical research area that seeks to decode human emotions from diverse data modalities. However, existing machine learning methods predominantly rely on predefined emotion taxonomies, which fail to capture the inherent complexity, subtlety, and multi-appraisal nature of human emotional experiences, as demonstrated by studies in psychology and cognitive science. To overcome this limitation, we advocate for introducing the concept of open vocabulary into MER. This paradigm shift aims to enable models to predict emotions beyond a fixed label space, accom"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.01495","kind":"arxiv","version":3},"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/2410.01495/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":"2410.01495","created_at":"2026-07-05T10:59:47.822100+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.01495v3","created_at":"2026-07-05T10:59:47.822100+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.01495","created_at":"2026-07-05T10:59:47.822100+00:00"},{"alias_kind":"pith_short_12","alias_value":"DY3CHACHXNKK","created_at":"2026-07-05T10:59:47.822100+00:00"},{"alias_kind":"pith_short_16","alias_value":"DY3CHACHXNKKQNEJ","created_at":"2026-07-05T10:59:47.822100+00:00"},{"alias_kind":"pith_short_8","alias_value":"DY3CHACH","created_at":"2026-07-05T10:59:47.822100+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.12018","citing_title":"MODF-SIR: A Multi-agent Omni-modal Distilled Framework for Social Intelligence Reasoning","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19950","citing_title":"AffectVerse: Emotional World Models for Multimodal Affective Computing","ref_index":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DY3CHACHXNKKQNEJL2SFHETNKJ","json":"https://pith.science/pith/DY3CHACHXNKKQNEJL2SFHETNKJ.json","graph_json":"https://pith.science/api/pith-number/DY3CHACHXNKKQNEJL2SFHETNKJ/graph.json","events_json":"https://pith.science/api/pith-number/DY3CHACHXNKKQNEJL2SFHETNKJ/events.json","paper":"https://pith.science/paper/DY3CHACH"},"agent_actions":{"view_html":"https://pith.science/pith/DY3CHACHXNKKQNEJL2SFHETNKJ","download_json":"https://pith.science/pith/DY3CHACHXNKKQNEJL2SFHETNKJ.json","view_paper":"https://pith.science/paper/DY3CHACH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.01495&json=true","fetch_graph":"https://pith.science/api/pith-number/DY3CHACHXNKKQNEJL2SFHETNKJ/graph.json","fetch_events":"https://pith.science/api/pith-number/DY3CHACHXNKKQNEJL2SFHETNKJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DY3CHACHXNKKQNEJL2SFHETNKJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DY3CHACHXNKKQNEJL2SFHETNKJ/action/storage_attestation","attest_author":"https://pith.science/pith/DY3CHACHXNKKQNEJL2SFHETNKJ/action/author_attestation","sign_citation":"https://pith.science/pith/DY3CHACHXNKKQNEJL2SFHETNKJ/action/citation_signature","submit_replication":"https://pith.science/pith/DY3CHACHXNKKQNEJL2SFHETNKJ/action/replication_record"}},"created_at":"2026-07-05T10:59:47.822100+00:00","updated_at":"2026-07-05T10:59:47.822100+00:00"}