{"id":"W2195207531","doi":"10.1109/iccvw.2015.12","title":"Do Deep Neural Networks Learn Facial Action Units When Doing Expression Recognition?","year":2015,"lang":"en","type":"article","venue":"","topic":"Face recognition and analysis","field":"Computer Science","cited_by":266,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Nvidia","keywords":"Convolutional neural network; Computer science; Classifier (UML); Artificial intelligence; Facial expression; Facial recognition system; Pattern recognition (psychology); Facial expression recognition; Face (sociological concept); Deep learning; Expression (computer science); Action recognition; Speech recognition; Machine learning","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002552336,0.0001302217,0.000136237,0.0001494053,0.0001687336,0.0003327509,0.0002972791,0.00009086996,0.0002686788],"category_scores_gemma":[0.00005965264,0.0001111142,0.00006500487,0.0005465899,0.00002088604,0.001003778,0.0001465663,0.0001911614,0.000279305],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003932806,"about_ca_system_score_gemma":0.00002881047,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003855135,"about_ca_topic_score_gemma":0.0000523538,"domain_scores_codex":[0.9987731,0.0001520024,0.0001997284,0.0003293029,0.0002943039,0.0002515729],"domain_scores_gemma":[0.9991173,0.00004809724,0.00008371672,0.0002347183,0.0002957851,0.0002204445],"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":[0.0000113969,0.00003608557,0.0002174888,0.000003191004,0.00001339466,0.000007050149,0.0005684961,0.006605838,0.0003915509,0.00009902193,0.002876718,0.9891698],"study_design_scores_gemma":[0.0005594345,0.00005807727,0.00006334849,0.0000215222,0.00001576068,0.00001865391,0.0007454269,0.9870541,0.002731612,0.001694615,0.006759736,0.0002777105],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01713086,0.00005678533,0.9721039,0.0005756783,0.000546651,0.00008311929,0.000001002238,0.0003325853,0.009169437],"genre_scores_gemma":[0.9717491,0.00002394647,0.0263168,0.0006174922,0.0002667416,0.00001238523,0.00003658663,0.00001090376,0.000966076],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9888921,"threshold_uncertainty_score":0.4531104,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08126738009899337,"score_gpt":0.2811073713752072,"score_spread":0.1998399912762138,"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."}}