{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001889845,0.0001608347,0.0001774917,0.00007030058,0.00007577574,0.00009651299,0.0004804965,0.0001373814,0.00008073089],"category_scores_gemma":[0.0001212827,0.0001360284,0.0002414493,0.0002245509,0.00009269486,0.0005183269,0.000133415,0.0001754628,0.00001471478],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006434121,"about_ca_system_score_gemma":0.00001774095,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001362627,"about_ca_topic_score_gemma":3.065453e-8,"domain_scores_codex":[0.9988693,2.803684e-8,0.0002937772,0.0002522494,0.0003577059,0.0002269419],"domain_scores_gemma":[0.9990073,0.00004901639,0.0001837414,0.00004236445,0.000646801,0.00007080899],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00008439684,0.0001268845,0.0001473021,0.0001580494,0.0001803463,6.702739e-7,0.0001961514,0.0003400712,0.7625583,0.1784646,0.03091199,0.02683126],"study_design_scores_gemma":[0.001043788,0.0001926165,0.0002120161,0.0005687819,0.00009135636,0.00008134043,0.0002634433,0.8847871,0.08189315,0.006016264,0.02425812,0.0005919983],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9815475,0.00007782359,0.002102145,0.0004027884,0.0006340054,0.0002190034,0.00001658715,0.00009430719,0.01490586],"genre_scores_gemma":[0.6147259,0.0002977104,0.3821873,0.0002934292,0.00164377,0.00009285732,0.00003019637,0.00008007343,0.0006486797],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.884447,"threshold_uncertainty_score":0.5547078,"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."}}