{"id":"W2069705645","doi":"10.1117/12.851424","title":"Automated person categorization for video surveillance using soft biometrics","year":2010,"lang":"en","type":"article","venue":"Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE","topic":"Face recognition and analysis","field":"Computer Science","cited_by":63,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Small Business Innovation Research","keywords":"Biometrics; Computer science; Artificial intelligence; Categorization; Computer vision; Feature extraction; Feature (linguistics); Facial recognition system; Categorical variable; Frame (networking); Face (sociological concept); Machine learning","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":[0.000808334,0.000259545,0.000357946,0.0003033716,0.0001409683,0.0002811106,0.001177864,0.0001791945,0.00000635806],"category_scores_gemma":[0.001257674,0.0002259975,0.000613749,0.001275209,0.0001283284,0.0008261343,0.0001253852,0.0002380298,0.00000141777],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001043658,"about_ca_system_score_gemma":0.00005385157,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001439936,"about_ca_topic_score_gemma":3.846945e-7,"domain_scores_codex":[0.998058,1.57346e-8,0.0005199407,0.0004412814,0.0006065622,0.0003742568],"domain_scores_gemma":[0.9964296,0.0002212374,0.0004387751,0.00007277048,0.002712269,0.0001253182],"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":[0.00001679016,0.00008812374,0.0004432184,0.0002686488,0.000242407,3.93298e-8,0.0001270534,0.0002428428,0.735149,0.261237,0.001147389,0.001037587],"study_design_scores_gemma":[0.0006276346,0.0001215866,0.0003781079,0.00006111123,0.00006494327,0.00001135527,0.0002733742,0.9179777,0.07819334,0.0007660601,0.001242072,0.0002826942],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9829378,0.00003593271,0.0138697,0.001697473,0.0004616055,0.0004230393,0.00004653553,0.0002844871,0.0002433952],"genre_scores_gemma":[0.5332288,0.00001987915,0.4661243,0.0001205145,0.0002957192,0.00008017715,0.00001534162,0.00004295772,0.00007230318],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9177349,"threshold_uncertainty_score":0.9215909,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01705325429510164,"score_gpt":0.2452410853839016,"score_spread":0.2281878310887999,"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."}}