{"id":"W7083333487","doi":"10.1016/j.engappai.2025.112447","title":"Enhanced multi-modal emotion recognition using the feature level fusion","year":2025,"lang":"en","type":"article","venue":"Engineering Applications of Artificial Intelligence","topic":"Library Science and Administration","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"National Key Research and Development Program of China; Fundamental Research Funds for the Central Universities; University of Science and Technology Beijing","keywords":"Emotion recognition; Modalities; Feature (linguistics); Process (computing); Encoder; Block (permutation group theory); Feature extraction; Feature learning; Artificial neural network","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":[],"consensus_categories":[],"category_scores_codex":[0.00036385,0.00007268224,0.00007366185,0.0001050393,0.0004483603,0.0000711355,0.000277477,0.00007770332,0.0000285721],"category_scores_gemma":[0.000150926,0.00006529128,0.00004441564,0.0009636336,0.0001449076,0.0003043303,0.00002584883,0.0001154019,0.00001514668],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000421951,"about_ca_system_score_gemma":0.0001463946,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002426685,"about_ca_topic_score_gemma":0.000118888,"domain_scores_codex":[0.999261,0.00003323546,0.0002138134,0.0001719404,0.0001708278,0.0001491656],"domain_scores_gemma":[0.9994759,0.0001072686,0.00007744812,0.0001783639,0.0001267788,0.00003424408],"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":[0.00001667684,0.0002083122,0.00007780528,0.00004530104,0.00001812327,2.31491e-7,0.006780453,0.02804917,0.2356643,0.1954988,0.00009903796,0.5335419],"study_design_scores_gemma":[0.00004284767,0.00003695541,0.001160299,0.0001723617,0.00003886163,7.116103e-7,0.01233297,0.2341633,0.7271813,0.01817922,0.006359645,0.0003315283],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07153317,0.00004147999,0.9260216,0.001216483,0.0002060447,0.0003896348,0.000009700853,0.0000620655,0.0005198108],"genre_scores_gemma":[0.9743857,0.00003346843,0.02507576,0.00003770062,0.0001232458,0.0000456155,0.00001120628,0.000004161749,0.0002831375],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9028525,"threshold_uncertainty_score":0.3448471,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08624060217338783,"score_gpt":0.3487356218247094,"score_spread":0.2624950196513216,"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."}}