{"id":"W2004586880","doi":"10.1007/s11263-007-0118-0","title":"Object Class Recognition and Localization Using Sparse Features with Limited Receptive Fields","year":2008,"lang":"en","type":"article","venue":"International Journal of Computer Vision","topic":"Visual Attention and Saliency Detection","field":"Computer Science","cited_by":377,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; University of British Columbia; Canadian Institute for Advanced Research","keywords":"Pooling; Pattern recognition (psychology); Artificial intelligence; Computer science; Object (grammar); Feature (linguistics); Position (finance); Matching (statistics); Cognitive neuroscience of visual object recognition; Class (philosophy); Computer vision; Mathematics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0001822989,0.0001045047,0.0001301198,0.0003285861,0.0001061435,0.0001410761,0.000277425,0.00006528642,0.00000937543],"category_scores_gemma":[0.0000186298,0.00008172553,0.00005855649,0.0002076372,0.0000452445,0.0009576621,0.00008545658,0.0001707435,0.000004917315],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006206792,"about_ca_system_score_gemma":0.0000488875,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001354669,"about_ca_topic_score_gemma":0.000005026339,"domain_scores_codex":[0.9988158,0.00009557606,0.0003030977,0.0001697473,0.0005229856,0.0000928116],"domain_scores_gemma":[0.998661,0.00005218306,0.0003192811,0.00008558797,0.0008149575,0.00006698449],"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":[0.001597311,0.0009770201,0.01008075,0.00003421124,0.0005421842,0.001302554,0.007239413,0.04471041,0.007679441,0.001341614,0.006099695,0.9183954],"study_design_scores_gemma":[0.003511599,0.004012668,0.07785964,0.0007880864,0.00003872999,0.01618264,0.00009172713,0.8835236,0.007701782,0.003629418,0.002147093,0.0005130618],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3811273,0.00002763702,0.6177726,0.0002174033,0.000747135,0.0000381678,7.238499e-7,0.00001912667,0.00004995326],"genre_scores_gemma":[0.9595682,0.0001084346,0.03948484,0.0004868392,0.0003213992,4.766529e-7,0.000004531269,0.000006152853,0.00001913115],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9178823,"threshold_uncertainty_score":0.333267,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03865115523951647,"score_gpt":0.2939910873716738,"score_spread":0.2553399321321574,"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."}}