{"id":"W4249224795","doi":"10.1109/icpr.2004.1334458","title":"Pruning local feature correspondences using shape context","year":2004,"lang":"en","type":"article","venue":"Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004.","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Artificial intelligence; Outlier; Robustness (evolution); Pattern recognition (psychology); Shape context; Computer science; Computer vision; Optimal distinctiveness theory; Feature extraction; Scale-invariant feature transform; Mathematics; Image (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":[0.0002964524,0.0003122104,0.0002676011,0.0002805836,0.0002536559,0.000327007,0.001814877,0.0001137468,0.0002355841],"category_scores_gemma":[0.0001860897,0.0002496919,0.0001538762,0.0004397097,0.0002293452,0.001324313,0.0003003579,0.0004559959,0.0000915788],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002487546,"about_ca_system_score_gemma":0.0002052025,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006855804,"about_ca_topic_score_gemma":0.00001145813,"domain_scores_codex":[0.9976658,0.00001936589,0.0004579361,0.0005934561,0.0008935175,0.0003699214],"domain_scores_gemma":[0.9977256,0.0000513934,0.0005499777,0.0002055892,0.001344319,0.0001231196],"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":[0.0002182666,0.0005535248,0.008144938,0.0001141119,0.0001836891,0.00001806161,0.002727028,0.0009167867,0.0182698,0.02955581,0.003738908,0.9355591],"study_design_scores_gemma":[0.007659667,0.0008616555,0.01113573,0.01006243,0.0001190722,0.0008085906,0.006181238,0.5120278,0.2573294,0.1866854,0.004423484,0.002705541],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2853651,0.0003237977,0.6753591,0.01727989,0.003546128,0.0009113254,0.0001150306,0.0003673007,0.01673238],"genre_scores_gemma":[0.9858183,0.00003099158,0.01128552,0.002225939,0.0001483678,0.00001706256,0.000008176325,0.00002282459,0.0004427828],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9328535,"threshold_uncertainty_score":0.9999955,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05522743208844295,"score_gpt":0.3020268910275903,"score_spread":0.2467994589391474,"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."}}