{"id":"W4405304022","doi":"10.1109/taffc.2024.3516822","title":"FedAR: Federated Artificial Resampling for Imbalanced Facial Emotion Recognition","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Affective Computing","topic":"Face recognition and analysis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Emotion recognition; Resampling; Computer science; Artificial intelligence; Facial expression; Affective computing; Emotion detection; Speech recognition; Pattern recognition (psychology); Emotion classification; Facial recognition system; Psychology; Machine learning","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":[0.0004390543,0.0002228842,0.0002335965,0.0004302988,0.0008064677,0.0006945973,0.0001592217,0.0001150243,0.00002633325],"category_scores_gemma":[0.00002861695,0.0002311028,0.0003158629,0.0009260127,0.00003286038,0.0004169094,0.00000307829,0.0003201756,0.0001796416],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001871362,"about_ca_system_score_gemma":0.00007429726,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001761711,"about_ca_topic_score_gemma":0.00003109868,"domain_scores_codex":[0.9983055,0.0001475968,0.0003105001,0.0006692569,0.000224351,0.0003428235],"domain_scores_gemma":[0.9989042,0.0005660882,0.0000686112,0.0001487431,0.0002237157,0.00008865867],"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":[0.00003239614,0.0001047654,0.000001343494,0.00005245724,0.0001068777,0.000005073407,0.0004202606,0.01572562,0.01275214,0.000210579,0.00006858377,0.9705199],"study_design_scores_gemma":[0.0003128771,0.0001851183,0.00003866727,0.0002430766,0.00005158303,0.00001247511,0.0001201525,0.9092629,0.08697473,0.002385917,0.0001236316,0.0002888508],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04877101,0.00002271563,0.9471866,0.0003905476,0.002002083,0.0004423859,0.00004630081,0.0009103522,0.0002279938],"genre_scores_gemma":[0.9858347,0.000008744318,0.01365277,0.0001295373,0.0002221856,0.00004476299,0.0000212898,0.00002444304,0.00006157252],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9702311,"threshold_uncertainty_score":0.9424098,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04156447279572322,"score_gpt":0.2971260507360293,"score_spread":0.2555615779403061,"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."}}