{"id":"W3091389496","doi":"10.1109/ijcnn48605.2020.9207250","title":"Continuous emotion recognition via deep convolutional autoencoder and support vector regressor","year":2020,"lang":"en","type":"article","venue":"Espace ÉTS (ETS)","topic":"Emotion and Mood Recognition","field":"Psychology","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"École de Technologie Supérieure; Université du Québec à Montréal","funders":"","keywords":"Autoencoder; Artificial intelligence; Computer science; Concordance correlation coefficient; Valence (chemistry); Arousal; Convolutional neural network; Preprocessor; Transfer of learning; Deep learning; Pattern recognition (psychology); Support vector machine; Facial expression; Feature extraction; Emotion recognition; Correlation; Machine learning; Speech recognition; Psychology; Mathematics","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":["insufficient_payload"],"category_scores_codex":[0.000212655,0.000215618,0.0002539996,0.0001016701,0.0001409903,0.00004638045,0.00008277071,0.0002357263,0.007919035],"category_scores_gemma":[0.0001348053,0.0002221263,0.00008912121,0.0001883529,0.0001155753,0.000189606,0.0000374236,0.0002770211,0.003166642],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004060163,"about_ca_system_score_gemma":0.00003262854,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002284624,"about_ca_topic_score_gemma":0.00003710407,"domain_scores_codex":[0.9984146,0.0002118056,0.0002928695,0.0005197526,0.0002272742,0.000333711],"domain_scores_gemma":[0.9991469,0.00008077989,0.0001788243,0.0001587756,0.0001707022,0.0002640461],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.003130009,0.001819386,0.01599457,0.0004228138,0.0009563586,0.0005422516,0.04120123,0.00003357701,0.02393718,0.01224239,0.2499413,0.6497789],"study_design_scores_gemma":[0.02444199,0.005069622,0.6463469,0.0004059032,0.0009058096,0.001896164,0.01054298,0.01930047,0.006700553,0.007539939,0.2729855,0.003864215],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7170372,0.0009701325,0.1181823,0.04990708,0.006427786,0.002329999,0.0003790535,0.001529102,0.1032374],"genre_scores_gemma":[0.9887645,0.00004106628,0.001625185,0.003284102,0.0006389334,0.000058168,0.0004699906,0.00004682154,0.005071297],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6459147,"threshold_uncertainty_score":0.9976095,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02983623259757149,"score_gpt":0.2802754166851131,"score_spread":0.2504391840875416,"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."}}