{"id":"W2148903555","doi":"10.1109/camp.1995.521022","title":"Visual attention: detecting abrupt onsets within the selective tuning model","year":2002,"lang":"en","type":"article","venue":"","topic":"Visual Attention and Saliency Detection","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Salient; Artificial intelligence; Visual attention; Sensory cue; Computational model; Dimension (graph theory); Computer vision; Human–computer interaction; Perception; Psychology; Neuroscience","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":[0.0004184566,0.0001401596,0.0001043482,0.0001028472,0.0006778635,0.0002532548,0.0004354237,0.00005873548,0.0000483871],"category_scores_gemma":[0.00005906199,0.00009886349,0.00009580782,0.000675995,0.00004048369,0.0006009927,0.000141819,0.0002528418,0.0002122065],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005774371,"about_ca_system_score_gemma":0.00001748633,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002607741,"about_ca_topic_score_gemma":0.00004528696,"domain_scores_codex":[0.9986403,0.0001196541,0.0002610354,0.0003776272,0.0003425665,0.0002588025],"domain_scores_gemma":[0.9993622,0.00005878565,0.0001141005,0.0002792286,0.0001148555,0.00007078707],"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":[0.00006308156,0.001870441,0.004679461,0.00007653416,0.0003784894,0.00007003336,0.03375086,0.07414455,0.1567548,0.2814188,0.009180322,0.4376126],"study_design_scores_gemma":[0.0001802976,0.0001181156,0.0006548635,0.000009397854,0.000005553368,0.00005766321,0.0002264034,0.9944414,0.002660031,0.001449591,0.00004509508,0.0001515153],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1586649,0.00002240452,0.830142,0.0008104413,0.0003516654,0.0001369826,1.875028e-7,0.0004116294,0.009459735],"genre_scores_gemma":[0.9884167,0.000002612686,0.007279259,0.0005538804,0.00005451736,0.00001909955,2.932639e-7,0.000009458164,0.003664177],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9202969,"threshold_uncertainty_score":0.5213646,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0353422250811722,"score_gpt":0.281495096194302,"score_spread":0.2461528711131298,"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."}}