{"id":"W1970428255","doi":"10.1109/acvmot.2005.95","title":"Pre-Attentive Face Detection for Foveated Wide-Field Surveillance","year":2005,"lang":"en","type":"article","venue":"","topic":"Video Surveillance and Tracking Methods","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Artificial intelligence; Computer vision; Computer science; Image resolution; Face (sociological concept); Probabilistic logic; Parametric statistics; Field of view; Field (mathematics); Object detection; Pattern recognition (psychology); 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":[0.0007379376,0.0001427843,0.000179285,0.00007236481,0.0001383891,0.0001276953,0.0004512809,0.00008409502,0.00001561701],"category_scores_gemma":[0.0003274862,0.000126922,0.0001014971,0.000314333,0.00001540295,0.0004862741,0.00008089725,0.0001026811,0.00004150753],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003719596,"about_ca_system_score_gemma":0.00002610683,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005048826,"about_ca_topic_score_gemma":0.0004305289,"domain_scores_codex":[0.9987456,0.0001065952,0.0002241789,0.0004301044,0.0001671721,0.0003263245],"domain_scores_gemma":[0.9984529,0.0008098652,0.0000845113,0.0004418794,0.0001452854,0.00006556025],"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":[0.00006587255,0.00007981956,0.0161251,0.00002183727,0.000055714,0.000001841445,0.0005283839,0.0008941412,0.007362301,0.002770494,0.002072114,0.9700224],"study_design_scores_gemma":[0.002082641,0.0007705456,0.1943906,0.00003051147,0.00001046327,0.00002783479,0.0000613664,0.2468536,0.4653691,0.005345848,0.0840582,0.0009992585],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03711727,0.00007190547,0.9574312,0.002378374,0.0004143977,0.0003062385,0.000002049444,0.0003777109,0.00190086],"genre_scores_gemma":[0.8827823,0.00001120063,0.114876,0.0009808355,0.0001041713,0.00004253957,0.000001583628,0.000009969823,0.001191418],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9690231,"threshold_uncertainty_score":0.5175727,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01843738379682973,"score_gpt":0.2955665255908486,"score_spread":0.2771291417940189,"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."}}