{"id":"W4312102722","doi":"10.1109/tencon55691.2022.9977693","title":"Combating Uncertainty and Class Imbalance in Facial Expression Recognition","year":2022,"lang":"en","type":"article","venue":"TENCON 2022 - 2022 IEEE Region 10 Conference (TENCON)","topic":"Emotion and Mood Recognition","field":"Psychology","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Windsor","funders":"Natural Science Foundation of Anhui Province; National Natural Science Foundation of China","keywords":"Computer science; Class (philosophy); Facial expression; Feature (linguistics); Artificial intelligence; Pattern recognition (psychology); Block (permutation group theory); Machine learning; Expression (computer science); Facial recognition system; Intersection (aeronautics); Noise (video); Fuzzy logic; Data mining; Mathematics; Image (mathematics); 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003057352,0.001053064,0.001210328,0.001110433,0.0006736211,0.0009786404,0.001196001,0.0007742764,0.0009020559],"category_scores_gemma":[0.005585749,0.0003839493,0.0008461556,0.0007150829,0.0008040867,0.002286033,0.001842766,0.001676414,0.0002894855],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009976194,"about_ca_system_score_gemma":0.0007347654,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003951489,"about_ca_topic_score_gemma":0.004197087,"domain_scores_codex":[0.9983333,0.0003490378,0.00009036683,0.0004409601,0.0005487893,0.0002376079],"domain_scores_gemma":[0.9986699,0.0005989287,0.0001895919,0.0002005666,0.0002794126,0.00006164689],"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":[0.0007561017,0.0002586649,0.01167796,0.00009659631,0.0001890023,0.0002499387,0.000511375,0.1501847,0.03433953,0.006617426,0.003684202,0.7914345],"study_design_scores_gemma":[0.00001025297,0.00008212273,0.005326895,0.00001385335,0.00003990656,0.0001087799,0.00009327617,0.9744211,0.01058912,0.008150619,0.001141251,0.00002270891],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.178977,0.0009922958,0.8148292,0.0006439828,0.0001301538,0.0001163754,0.0001784295,0.001121805,0.003010705],"genre_scores_gemma":[0.9367688,0.0003564874,0.06021101,0.0002642785,0.0001412077,0.0001029891,0.0003497289,0.0000864631,0.001719158],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003951489,"threshold_uncertainty_score":0.01616901,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06700933578632123,"score_gpt":0.30304759493473,"score_spread":0.2360382591484088,"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."}}