{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:W3RA2TFKXTPUYDDGBCT45PBTU7","short_pith_number":"pith:W3RA2TFK","schema_version":"1.0","canonical_sha256":"b6e20d4caabcdf4c0c6608a7cebc33a7f1882fc97c786778149f0e0837548a27","source":{"kind":"arxiv","id":"1906.10623","version":1},"attestation_state":"computed","paper":{"title":"Emotion Recognition Using Fusion of Audio and Video Features","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alessandro L. Koerich, Juan D. S. Ortega, Patrick Cardinal","submitted_at":"2019-06-25T16:13:41Z","abstract_excerpt":"In this paper we propose a fusion approach to continuous emotion recognition that combines visual and auditory modalities in their representation spaces to predict the arousal and valence levels. The proposed approach employs a pre-trained convolution neural network and transfer learning to extract features from video frames that capture the emotional content. For the auditory content, a minimalistic set of parameters such as prosodic, excitation, vocal tract, and spectral descriptors are used as features. The fusion of these two modalities is carried out at a feature level, before training a "},"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":"1906.10623","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-25T16:13:41Z","cross_cats_sorted":["cs.SD","eess.AS","stat.ML"],"title_canon_sha256":"ad6c2c7d08a1fe4f8602f2467b206abc0fe46fa8b81339bbb46a2d610af9ec6c","abstract_canon_sha256":"013fd877b7cd2621719218e1b9c07634570b5cd32812c7d95944113e0eddeba7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:42:15.765608Z","signature_b64":"5hw37oum8HwuMSj3yIeRCTSRvnv+WNtibgkokWBTNHf8uO3AkDiH9pqPMsGlVwPTF5kbrxEIxsVVBzjOYIHvAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b6e20d4caabcdf4c0c6608a7cebc33a7f1882fc97c786778149f0e0837548a27","last_reissued_at":"2026-05-17T23:42:15.764914Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:42:15.764914Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Emotion Recognition Using Fusion of Audio and Video Features","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alessandro L. Koerich, Juan D. S. Ortega, Patrick Cardinal","submitted_at":"2019-06-25T16:13:41Z","abstract_excerpt":"In this paper we propose a fusion approach to continuous emotion recognition that combines visual and auditory modalities in their representation spaces to predict the arousal and valence levels. The proposed approach employs a pre-trained convolution neural network and transfer learning to extract features from video frames that capture the emotional content. For the auditory content, a minimalistic set of parameters such as prosodic, excitation, vocal tract, and spectral descriptors are used as features. The fusion of these two modalities is carried out at a feature level, before training a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.10623","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":""},"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":"1906.10623","created_at":"2026-05-17T23:42:15.765026+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.10623v1","created_at":"2026-05-17T23:42:15.765026+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.10623","created_at":"2026-05-17T23:42:15.765026+00:00"},{"alias_kind":"pith_short_12","alias_value":"W3RA2TFKXTPU","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_16","alias_value":"W3RA2TFKXTPUYDDG","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_8","alias_value":"W3RA2TFK","created_at":"2026-05-18T12:33:30.264802+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/W3RA2TFKXTPUYDDGBCT45PBTU7","json":"https://pith.science/pith/W3RA2TFKXTPUYDDGBCT45PBTU7.json","graph_json":"https://pith.science/api/pith-number/W3RA2TFKXTPUYDDGBCT45PBTU7/graph.json","events_json":"https://pith.science/api/pith-number/W3RA2TFKXTPUYDDGBCT45PBTU7/events.json","paper":"https://pith.science/paper/W3RA2TFK"},"agent_actions":{"view_html":"https://pith.science/pith/W3RA2TFKXTPUYDDGBCT45PBTU7","download_json":"https://pith.science/pith/W3RA2TFKXTPUYDDGBCT45PBTU7.json","view_paper":"https://pith.science/paper/W3RA2TFK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.10623&json=true","fetch_graph":"https://pith.science/api/pith-number/W3RA2TFKXTPUYDDGBCT45PBTU7/graph.json","fetch_events":"https://pith.science/api/pith-number/W3RA2TFKXTPUYDDGBCT45PBTU7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/W3RA2TFKXTPUYDDGBCT45PBTU7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/W3RA2TFKXTPUYDDGBCT45PBTU7/action/storage_attestation","attest_author":"https://pith.science/pith/W3RA2TFKXTPUYDDGBCT45PBTU7/action/author_attestation","sign_citation":"https://pith.science/pith/W3RA2TFKXTPUYDDGBCT45PBTU7/action/citation_signature","submit_replication":"https://pith.science/pith/W3RA2TFKXTPUYDDGBCT45PBTU7/action/replication_record"}},"created_at":"2026-05-17T23:42:15.765026+00:00","updated_at":"2026-05-17T23:42:15.765026+00:00"}