{"id":"W2036024554","doi":"10.1109/icmew.2014.6890712","title":"A semi-supervised temporal clustering method for facial emotion analysis","year":2014,"lang":"en","type":"article","venue":"","topic":"Face and Expression Recognition","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Cluster analysis; Categorization; Artificial intelligence; Kernel (algebra); Pattern recognition (psychology); Machine learning; Mathematics","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":[0.000417891,0.00008114148,0.0001505117,0.0001630552,0.000107118,0.0001141884,0.0002387521,0.00005481855,0.00006045735],"category_scores_gemma":[0.00003579085,0.00006687055,0.0001496615,0.0003822089,0.000005183374,0.0003136864,0.00008817638,0.00003768385,0.00003080686],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001107492,"about_ca_system_score_gemma":0.000009295002,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009078167,"about_ca_topic_score_gemma":0.00007278757,"domain_scores_codex":[0.9992018,0.00007721753,0.0001578279,0.0002753862,0.0001292676,0.0001585507],"domain_scores_gemma":[0.9995157,0.00008335036,0.00004392269,0.0002329013,0.00006373749,0.000060388],"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":[0.00002752311,0.00007783117,0.00141023,0.00004005379,0.0002067389,7.060148e-7,0.001046657,0.006825924,0.01441955,0.002061349,0.003612505,0.9702709],"study_design_scores_gemma":[0.0002932917,0.00004146316,0.0005069652,0.000004649347,0.00003930682,7.153191e-7,0.00003357761,0.9911047,0.003540425,0.001274674,0.003056567,0.0001037167],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.007806011,0.000001948731,0.9896946,0.0005582357,0.0001467535,0.000121111,0.000002214766,0.0001464307,0.001522705],"genre_scores_gemma":[0.3655412,7.982902e-7,0.6334061,0.000476303,0.00006362342,0.00002295231,0.00002034715,0.000003739379,0.0004649757],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9842787,"threshold_uncertainty_score":0.2726902,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02566355636187622,"score_gpt":0.2933704078626007,"score_spread":0.2677068515007245,"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."}}