{"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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001314717,0.0002256437,0.000220148,0.0005821373,0.0007434663,0.0003188533,0.00009958867,0.0003472938,0.00233135],"category_scores_gemma":[0.0001012461,0.0002196537,0.0002330579,0.0008878472,0.0002600823,0.0002908027,0.00001603381,0.0002895543,0.0001559172],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001276181,"about_ca_system_score_gemma":0.0001978785,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007383287,"about_ca_topic_score_gemma":0.00003686901,"domain_scores_codex":[0.9974271,0.0001520589,0.0005739264,0.001006463,0.0004160235,0.0004244014],"domain_scores_gemma":[0.9985498,0.00003626764,0.0002809046,0.0005839168,0.0004298888,0.0001192265],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0005706431,0.002149604,0.01597365,0.0003293991,0.0001876231,0.0007762091,0.002189077,0.0007933688,0.3582343,0.0002652585,0.04445686,0.574074],"study_design_scores_gemma":[0.01249175,0.0005599094,0.1602448,0.002392668,0.0007486031,0.002141946,0.002621159,0.03047099,0.5466905,0.06010872,0.1781991,0.003329795],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9241741,0.0001106437,0.01838206,0.0003396445,0.02940736,0.000698906,0.00002063352,0.0002310363,0.02663565],"genre_scores_gemma":[0.9852483,0.000002041949,0.002075042,0.0002261662,0.0001520013,0.0000350735,0.0008050983,0.00002350277,0.01143273],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5707442,"threshold_uncertainty_score":0.9985806,"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."}}