{"id":"W2896868133","doi":"10.1145/3240508.3240613","title":"Personalized Multiple Facial Action Unit Recognition through Generative Adversarial Recognition Network","year":2018,"lang":"en","type":"article","venue":"","topic":"Face recognition and analysis","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"University of Northern British Columbia","keywords":"Computer science; Artificial intelligence; Classifier (UML); Generative adversarial network; Generative grammar; Pattern recognition (psychology); Leverage (statistics); Adversarial system; Facial recognition system; Face (sociological concept); Domain (mathematical analysis); Domain adaptation; Benchmark (surveying); Facial expression; Computer vision; Deep learning; Mathematics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0002922349,0.0002253944,0.0002376111,0.0001154436,0.0005778991,0.0002352614,0.000268693,0.0001597747,0.00209226],"category_scores_gemma":[0.0001192736,0.000212917,0.0001933018,0.0008841209,0.0001441722,0.001437485,0.00009194833,0.000174721,0.00258623],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000687413,"about_ca_system_score_gemma":0.00007761382,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001847873,"about_ca_topic_score_gemma":0.0006210025,"domain_scores_codex":[0.9980881,0.0002811961,0.0003210056,0.0005663132,0.000348845,0.0003945174],"domain_scores_gemma":[0.9988286,0.000119003,0.0001684649,0.0002450365,0.0005268463,0.0001120854],"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":[0.0002987625,0.0003096948,0.0003172627,0.00001704724,0.0003326202,0.00001089453,0.002992405,0.00008913861,0.007101781,0.00188973,0.01806201,0.9685786],"study_design_scores_gemma":[0.01158255,0.001333127,0.001226829,0.0002044164,0.0004004134,0.00008585535,0.002744779,0.6307478,0.1031676,0.1057465,0.1399872,0.002772908],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03331388,0.0000206818,0.9481269,0.0008840891,0.00151315,0.0002829863,0.00003328608,0.0004650875,0.01535996],"genre_scores_gemma":[0.6092559,0.0002753604,0.3748762,0.005042837,0.00610804,0.0001200883,0.0009237357,0.00004354221,0.00335431],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9658058,"threshold_uncertainty_score":0.9988199,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1078290960325501,"score_gpt":0.3035069408452722,"score_spread":0.1956778448127221,"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."}}