{"id":"W4407559183","doi":"10.1038/s41598-025-89202-x","title":"MemoCMT: multimodal emotion recognition using cross-modal transformer-based feature fusion","year":2025,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Emotion and Mood Recognition","field":"Psychology","cited_by":66,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Modal; Computer science; Emotion recognition; Transformer; Fusion; Pattern recognition (psychology); Artificial intelligence; Speech recognition; Feature (linguistics); Engineering; Materials science; Voltage; Electrical engineering","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006890844,0.001151342,0.0006689041,0.001192769,0.0003619304,0.0007823771,0.0008895408,0.000699028,0.005209986],"category_scores_gemma":[0.001927832,0.0001970043,0.0009152946,0.0007082135,0.0002342149,0.001414051,0.001955384,0.0007378387,0.002240155],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004215029,"about_ca_system_score_gemma":0.0002729753,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001895985,"about_ca_topic_score_gemma":0.002514508,"domain_scores_codex":[0.9996052,0.000058538,0.0000213627,0.0001567368,0.0001022993,0.00005595529],"domain_scores_gemma":[0.9997348,0.00006838005,0.00002570201,0.00005211534,0.00009546369,0.00002344519],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0007493021,0.0002865878,0.003326978,0.0002720521,0.000237425,0.0003239309,0.0002541792,0.006929763,0.0840808,0.002366713,0.03609226,0.8650801],"study_design_scores_gemma":[0.0001155308,0.0005830324,0.01349852,0.00008495741,0.0002718191,0.0009839872,0.000307108,0.827665,0.1130683,0.014494,0.02876837,0.0001593535],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08715228,0.001841513,0.8623874,0.0004283704,0.0006855081,0.0004865088,0.003892481,0.03321912,0.009906805],"genre_scores_gemma":[0.5951239,0.0006859159,0.38028,0.0008122885,0.000271059,0.0006579945,0.009844781,0.001110798,0.01121323],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005209986,"threshold_uncertainty_score":0.01742911,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03665860509373072,"score_gpt":0.3483388481411197,"score_spread":0.311680243047389,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}