{"id":"W4383560118","doi":"10.1007/s11042-023-15888-8","title":"Majority biased facial emotion recognition using residual variational autoencoders","year":2023,"lang":"en","type":"article","venue":"Multimedia Tools and Applications","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Autoencoder; Computer science; Oversampling; Artificial intelligence; Undersampling; Pattern recognition (psychology); Hyperparameter; Residual; Confusion matrix; Classifier (UML); Machine learning; Deep learning; Algorithm; Bandwidth (computing)","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":[0.0003063786,0.0001080765,0.0001023262,0.0001687231,0.0003300602,0.0002025274,0.0002880022,0.00009045716,0.00001717193],"category_scores_gemma":[0.0001065303,0.0001173305,0.00002670826,0.0007083375,0.00006482447,0.0006808524,0.0001156719,0.0001097072,0.0001556043],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005120451,"about_ca_system_score_gemma":0.0000760945,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003232673,"about_ca_topic_score_gemma":0.00000383345,"domain_scores_codex":[0.9988862,0.00005043015,0.0002432919,0.0003997508,0.0002267739,0.0001936104],"domain_scores_gemma":[0.9991394,0.000183159,0.0001160103,0.0003622189,0.000120058,0.00007913257],"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":[0.000004798534,0.0001234728,0.0008109617,0.0000283733,0.00001980826,0.000001671464,0.0005376585,0.0002819716,0.01543934,0.01945286,0.003266425,0.9600326],"study_design_scores_gemma":[0.0003804885,0.00001770861,0.06345506,0.00001491639,0.0000126768,0.000004947144,0.00005603758,0.9066831,0.002673381,0.01865921,0.007777809,0.0002646202],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.006381712,0.000007382905,0.9903708,0.001089292,0.0000864407,0.0005356168,0.0004355115,0.0008503695,0.0002428625],"genre_scores_gemma":[0.08657812,0.00007437878,0.9091914,0.0002408284,0.000352561,0.0008152646,0.002629712,0.00001963243,0.00009815528],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9597681,"threshold_uncertainty_score":0.4784597,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1008491677308637,"score_gpt":0.3087321104849359,"score_spread":0.2078829427540723,"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."}}