{"id":"W2122015342","doi":"10.1109/cvpr.2005.235","title":"Multi-Image Matching Using Multi-Scale Oriented Patches","year":2005,"lang":"en","type":"article","venue":"","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":401,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"RANSAC; Artificial intelligence; Pattern recognition (psychology); Invariant (physics); Computer science; Feature extraction; Scale space; Matching (statistics); Feature (linguistics); Computer vision; Mathematics; Haar wavelet; Outlier; Panorama; Feature vector; Wavelet transform; Wavelet; Image (mathematics); Discrete wavelet transform; Image processing","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":[0.0002058632,0.0001890511,0.0001836202,0.0001035628,0.0001775823,0.000145673,0.000579127,0.00006623725,0.00002971562],"category_scores_gemma":[0.00003948332,0.0001631006,0.00008345074,0.000376582,0.00005111989,0.001991257,0.0003783773,0.0001760988,0.00007729512],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008133006,"about_ca_system_score_gemma":0.00003220707,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009225955,"about_ca_topic_score_gemma":0.00003889293,"domain_scores_codex":[0.9986571,0.00003986767,0.0002775276,0.0004435326,0.0002090721,0.0003728692],"domain_scores_gemma":[0.9991093,0.00004480448,0.00008667664,0.0005341586,0.0001122252,0.0001128312],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001045431,0.0004985449,0.00128174,0.00002721043,0.00002005165,0.00004032834,0.002304462,0.0001613084,0.7791232,0.001492792,0.0002703589,0.2147696],"study_design_scores_gemma":[0.0005716328,0.00003668791,0.0008533744,0.00003697365,0.000005640622,0.00002845941,0.0001354429,0.3788945,0.612195,0.0003776541,0.006480127,0.0003845204],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01557235,0.0001003691,0.9824229,0.0002306583,0.00008679117,0.0001777798,0.000001804812,0.0009888965,0.0004183806],"genre_scores_gemma":[0.09490836,0.00002258725,0.9035814,0.0005260108,0.00006346695,0.00000540038,0.000001230089,0.00001667342,0.0008748962],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3787332,"threshold_uncertainty_score":0.6651048,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03801778359576503,"score_gpt":0.3286674344129686,"score_spread":0.2906496508172036,"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."}}