{"id":"W2163522917","doi":"10.1109/cvpr.2004.409","title":"Object Class Recognition with Many Local Features","year":2005,"lang":"en","type":"article","venue":"","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":46,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Artificial intelligence; Computer science; Clutter; Cognitive neuroscience of visual object recognition; Pattern recognition (psychology); Class (philosophy); Statistical model; Object (grammar); Probabilistic logic; 3D single-object recognition; Set (abstract data type); Object detection; Object model; Matching (statistics); Machine learning; Mixture model; Invariant (physics); Scale (ratio); Mathematics; Statistics","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":[0.0000808657,0.00009974802,0.00008702414,0.00006003442,0.00005977571,0.00008141685,0.0002905127,0.00004436481,0.00003592545],"category_scores_gemma":[0.00001067047,0.00006944354,0.00002866076,0.0002478643,0.00004425117,0.0008821902,0.00007228192,0.000123836,0.0001085485],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003867525,"about_ca_system_score_gemma":0.00002430894,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001043812,"about_ca_topic_score_gemma":0.000026426,"domain_scores_codex":[0.9992844,0.00001855553,0.00009270593,0.0002503907,0.0001690707,0.0001848636],"domain_scores_gemma":[0.9995337,0.00003198968,0.00003328063,0.0002732596,0.00007370501,0.00005406901],"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":[0.00001296104,0.00002717141,0.00001842874,0.000003053593,0.00000457053,0.00001178484,0.00004244423,0.000009033015,0.0004730076,0.005749253,0.004665698,0.9889826],"study_design_scores_gemma":[0.0003763988,0.0005538657,0.001292279,0.00004846098,0.000007483852,0.0001987745,0.00004702631,0.005074626,0.9040818,0.01346706,0.07441874,0.0004335506],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.000627001,0.00009445323,0.967427,0.0009043558,0.00002333083,0.0001025434,6.22288e-7,0.000621064,0.03019967],"genre_scores_gemma":[0.45638,0.00004665243,0.5396235,0.001848512,0.00008193792,0.00001095316,0.00000243596,0.000007914435,0.001998105],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9885491,"threshold_uncertainty_score":0.2831826,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01270437364790963,"score_gpt":0.2583989903167209,"score_spread":0.2456946166688113,"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."}}