{"id":"W2035669857","doi":"10.1117/12.436980","title":"<title>Facial expression recognition using constructive neural networks</title>","year":2001,"lang":"en","type":"article","venue":"Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE","topic":"Face and Expression Recognition","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"Instituto de Telecomunicações","keywords":"Constructive; Pruning; Computer science; Artificial neural network; Artificial intelligence; Face (sociological concept); Discrete cosine transform; Feature (linguistics); Constructive proof; Process (computing); Pattern recognition (psychology); Speech recognition; Facial expression; Expression (computer science); Facial recognition system; Feature extraction; Image (mathematics); Computer vision; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003537663,0.001013187,0.001078238,0.0006437267,0.0003905534,0.001678483,0.001504453,0.0009799639,0.1297132],"category_scores_gemma":[0.0009948764,0.0002199144,0.0005471212,0.0009438737,0.0004690248,0.001809992,0.0007050927,0.001330559,0.08075646],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000717594,"about_ca_system_score_gemma":0.0004904725,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002793564,"about_ca_topic_score_gemma":0.002832007,"domain_scores_codex":[0.9996495,0.00003463893,0.0000201791,0.00009622596,0.0001598208,0.0000396359],"domain_scores_gemma":[0.9994599,0.0001060166,0.0000369175,0.00006634664,0.0002857884,0.00004496076],"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":[0.0003156062,0.0001349129,0.0002715952,0.001000245,0.00004532529,0.0002900136,0.00003145427,0.00483035,0.02794827,0.009177664,0.3824801,0.5734745],"study_design_scores_gemma":[0.00006423161,0.0003781187,0.001586457,0.0003382972,0.00007400039,0.0004071009,0.00004998805,0.1082563,0.03369457,0.007878179,0.8471817,0.00009098792],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.02125727,0.03384872,0.2672356,0.01206192,0.05895327,0.001165013,0.003920221,0.0178389,0.583719],"genre_scores_gemma":[0.09486023,0.02027101,0.06293309,0.002931891,0.004931637,0.0005241839,0.007902051,0.002408359,0.8032376],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.1297132,"threshold_uncertainty_score":0.4339337,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01741915977759414,"score_gpt":0.2330034137955895,"score_spread":0.2155842540179954,"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."}}