{"id":"W4410774247","doi":"10.1016/j.procs.2025.03.218","title":"Deep Facial Feature Fusion and Voting Strategies for Enhanced Emotion Recognition","year":2025,"lang":"en","type":"article","venue":"Procedia Computer Science","topic":"Emotion and Mood Recognition","field":"Psychology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Future Earth","funders":"","keywords":"Computer science; Voting; Emotion recognition; Feature (linguistics); Fusion; Artificial intelligence; Facial expression; Speech recognition; Pattern recognition (psychology); Facial recognition system","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":[0.0003236997,0.0001036091,0.0000988481,0.0002139693,0.0003485781,0.0001802944,0.0001268056,0.00008681088,0.00001853932],"category_scores_gemma":[0.00004911394,0.00009841927,0.0000290553,0.0004296938,0.0001471908,0.0003994069,0.00005859522,0.0001031095,0.00001761998],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002529406,"about_ca_system_score_gemma":0.0000895608,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003416621,"about_ca_topic_score_gemma":0.00001482266,"domain_scores_codex":[0.9990327,0.0000235558,0.0001366032,0.0004440243,0.0001224939,0.0002406192],"domain_scores_gemma":[0.9994675,0.00005702419,0.00006950636,0.00007981783,0.0002728607,0.00005330865],"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":[0.00003932889,0.0000570958,0.0001290464,0.0000781937,0.000006511812,4.558462e-7,0.002809724,0.00001334768,0.01146049,0.005123745,0.0005153316,0.9797667],"study_design_scores_gemma":[0.01427547,0.00286574,0.2359659,0.001981752,0.0002688682,0.0001909923,0.01196188,0.4296376,0.1001598,0.1929514,0.006862267,0.002878403],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2739359,0.00005000609,0.7200024,0.0003680359,0.001788384,0.0003631276,0.000002885794,0.00009413248,0.003395118],"genre_scores_gemma":[0.9760909,0.00000835731,0.02287935,0.0005068983,0.0002484666,0.00005475352,0.00001982041,0.00000496046,0.0001864814],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9768883,"threshold_uncertainty_score":0.4013421,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02381643086306556,"score_gpt":0.308157461173856,"score_spread":0.2843410303107904,"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."}}