{"id":"W2105464770","doi":"10.1109/cvpr.2006.200","title":"Multiclass Object Recognition with Sparse, Localized Features","year":2006,"lang":"en","type":"article","venue":"","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":459,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Artificial intelligence; Computer science; Pooling; Object (grammar); Cognitive neuroscience of visual object recognition; Pattern recognition (psychology); Feature (linguistics); Categorization; Matching (statistics); Position (finance); Class (philosophy); Task (project management); Computer vision; Scale (ratio); Feature extraction; Machine learning; Mathematics; Engineering","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":[0.00008787839,0.0001210751,0.0001176939,0.00007052468,0.00007030821,0.0001149803,0.0002674111,0.0000466014,0.00001897493],"category_scores_gemma":[0.00002011354,0.00008424394,0.00003455459,0.0003629167,0.00004357241,0.000618936,0.00006180664,0.00009784545,0.00004639869],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002631003,"about_ca_system_score_gemma":0.00002369095,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001667126,"about_ca_topic_score_gemma":0.00007023943,"domain_scores_codex":[0.9991584,0.00002917942,0.0001244404,0.000287235,0.0001913017,0.0002094807],"domain_scores_gemma":[0.999449,0.00005521086,0.00005092796,0.0002988951,0.0001071025,0.000038845],"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":[0.0001607659,0.0002589998,0.001094704,0.00003476125,0.00003014405,0.0002068039,0.000111214,0.0000797451,0.01624605,0.03567747,0.02952518,0.9165742],"study_design_scores_gemma":[0.000961507,0.0003332026,0.003546387,0.0000493065,0.000009725049,0.00009799704,0.00001758851,0.002498449,0.9129069,0.05846499,0.02067401,0.0004399798],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001763449,0.00008773788,0.9728583,0.0002280001,0.00003643485,0.0001702322,0.000001212081,0.000785972,0.02406864],"genre_scores_gemma":[0.2740569,0.00001888887,0.7231723,0.0004503108,0.0000543518,0.0000170358,0.000007630308,0.00001022705,0.002212385],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9161342,"threshold_uncertainty_score":0.3435368,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01419158525478288,"score_gpt":0.2502844115908242,"score_spread":0.2360928263360413,"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."}}