{"id":"W2951151581","doi":"10.48550/arxiv.1510.02969","title":"Do Deep Neural Networks Learn Facial Action Units When Doing Expression Recognition?","year":2015,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Emotion and Mood Recognition","field":"Psychology","cited_by":30,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Nvidia","keywords":"Convolutional neural network; Computer science; Classifier (UML); Artificial intelligence; Facial expression; Pattern recognition (psychology); Facial recognition system; Face (sociological concept); Facial expression recognition; Action recognition; Expression (computer science); Speech recognition","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":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0003470994,0.0004153399,0.000368648,0.0004014666,0.0002684364,0.00009858461,0.0003942243,0.0009788568,0.002248294],"category_scores_gemma":[0.00005310828,0.0004896545,0.0001987238,0.0004049746,0.000111607,0.0003116366,0.0004414659,0.001435172,0.0006915571],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000236466,"about_ca_system_score_gemma":0.00007247936,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001692946,"about_ca_topic_score_gemma":0.0001481658,"domain_scores_codex":[0.9973206,0.0006841878,0.0003056113,0.001092253,0.0001220003,0.0004753636],"domain_scores_gemma":[0.9980222,0.00009147585,0.0004327699,0.0005994927,0.0005491999,0.0003048636],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.003493247,0.001306094,0.007316013,0.0003159344,0.0009149358,0.001356424,0.009463958,0.491197,0.0003580494,0.003293164,0.03148984,0.4494953],"study_design_scores_gemma":[0.02473878,0.001701224,0.01048127,0.002418121,0.003280078,0.000366441,0.03817316,0.6968482,0.0009627418,0.155273,0.05612978,0.009627287],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7961149,0.0001756893,0.1408152,0.00007542954,0.007606317,0.0007693915,0.00007792156,0.0005896064,0.05377554],"genre_scores_gemma":[0.9933552,0.0001175803,0.0001371582,0.0001386125,0.0008217471,0.000005215242,0.0008168897,0.00005775912,0.004549845],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.439868,"threshold_uncertainty_score":0.9997555,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.203370727996214,"score_gpt":0.2602850645494182,"score_spread":0.05691433655320421,"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."}}