{"id":"W1991737658","doi":"10.1109/icmla.2012.178","title":"Cross-Domain Facial Expression Recognition Using Supervised Kernel Mean Matching","year":2012,"lang":"en","type":"article","venue":"","topic":"Face and Expression Recognition","field":"Computer Science","cited_by":36,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Discriminative model; Matching (statistics); Pattern recognition (psychology); Kernel (algebra); Computer science; Artificial intelligence; Support vector machine; Facial expression recognition; Class (philosophy); Facial expression; Domain (mathematical analysis); Expression (computer science); Machine learning; Facial recognition system; Mathematics; Statistics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009777537,0.0004752111,0.000823923,0.0008426135,0.0002703812,0.0004935474,0.000794459,0.0004813085,0.000741123],"category_scores_gemma":[0.002150705,0.0002119361,0.0006671787,0.0006980468,0.0003603471,0.0008702874,0.0009455862,0.0005655284,0.000578324],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003282477,"about_ca_system_score_gemma":0.0004020461,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00135514,"about_ca_topic_score_gemma":0.001417961,"domain_scores_codex":[0.9990682,0.0002603193,0.00004283583,0.0003329823,0.0002025809,0.0000930591],"domain_scores_gemma":[0.9992027,0.0001611728,0.0001131578,0.0002415478,0.000247954,0.00003344879],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0005509513,0.0003745919,0.005761437,0.00007492226,0.0001948699,0.0001088897,0.0001726349,0.06980801,0.1096237,0.002583102,0.002551492,0.8081954],"study_design_scores_gemma":[0.0000116616,0.00005931174,0.003901856,0.000003236926,0.00002137929,0.000138154,0.00005021227,0.97083,0.02212884,0.002241469,0.0005974208,0.00001641854],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1153615,0.0001453024,0.8822104,0.00005661858,0.00002427552,0.00003936048,0.00006074744,0.001241029,0.0008606623],"genre_scores_gemma":[0.8249242,0.00009415539,0.1729853,0.00005537169,0.00001868811,0.00006205736,0.0003626719,0.00011861,0.00137889],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00135514,"threshold_uncertainty_score":0.005170941,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05306481945402174,"score_gpt":0.2969890372087989,"score_spread":0.2439242177547771,"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."}}