{"id":"W1557370378","doi":"10.1007/11744078_3","title":"Sparse Flexible Models of Local Features","year":2006,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":44,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Artificial intelligence; Prior probability; Pattern recognition (psychology); Feature (linguistics); Representation (politics); Inference; Object (grammar); Matching (statistics); Class (philosophy); Cognitive neuroscience of visual object recognition; Machine learning; 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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005160546,0.0005237064,0.0006587913,0.0008406465,0.0001312323,0.0002062961,0.003348568,0.0003630471,0.000007529027],"category_scores_gemma":[0.00002931215,0.0004662037,0.0001823411,0.0007468805,0.00113573,0.001116973,0.001363368,0.000769872,0.000008680734],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002116621,"about_ca_system_score_gemma":0.0004248556,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005996595,"about_ca_topic_score_gemma":0.00002300409,"domain_scores_codex":[0.9964185,0.00002282261,0.0005867677,0.001311556,0.001049807,0.0006105173],"domain_scores_gemma":[0.9973623,0.0002647123,0.0003617826,0.001536065,0.0003505798,0.0001245454],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000008060648,0.00003286509,0.000004251678,0.0000463697,0.000006299979,0.00006796798,0.0001066778,0.1168255,0.0002240634,0.06985235,0.0002433137,0.8125823],"study_design_scores_gemma":[0.000159459,0.0002091994,0.00002754222,0.0003759281,0.000006433417,0.00005908885,7.307434e-8,0.2237371,0.07665512,0.6969403,0.001273057,0.0005566732],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.000005103389,0.001536008,0.9847642,0.0001662831,0.0004705421,0.0003165781,0.000007431393,0.0003087256,0.01242517],"genre_scores_gemma":[0.1224869,0.0001357165,0.8750293,0.0007373318,0.0002523334,0.000006862139,0.00000615003,0.00004408753,0.001301357],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8120255,"threshold_uncertainty_score":0.999779,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02240709996144876,"score_gpt":0.2696644613843076,"score_spread":0.2472573614228588,"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."}}