{"id":"W2123038104","doi":"10.1109/icip.2005.1529939","title":"Achieving efficient dense matching for uncalibrated images","year":2005,"lang":"en","type":"article","venue":"","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Windsor","funders":"","keywords":"Classification of discontinuities; Epipolar geometry; Matching (statistics); Artificial intelligence; Computer science; Similarity (geometry); Computer vision; Enhanced Data Rates for GSM Evolution; Pixel; Template matching; Mathematics; Pattern recognition (psychology); Algorithm; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007054086,0.0006433572,0.0009032213,0.001757661,0.0004842387,0.0008329656,0.001234661,0.0007745129,0.002058959],"category_scores_gemma":[0.0024267,0.0007425871,0.0006674433,0.001156993,0.0006117605,0.001825542,0.002407702,0.0008481992,0.001013685],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005313235,"about_ca_system_score_gemma":0.0007760662,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001687439,"about_ca_topic_score_gemma":0.002517523,"domain_scores_codex":[0.9988668,0.0001435266,0.00004420851,0.0001911972,0.0006453809,0.0001089377],"domain_scores_gemma":[0.9991798,0.0002174462,0.0001003423,0.0002915088,0.000173528,0.00003743948],"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":[0.0002725231,0.0001256857,0.0007999156,0.0002493269,0.0001082891,0.000242078,0.0003640841,0.06001972,0.2310631,0.02548886,0.002889918,0.6783766],"study_design_scores_gemma":[0.00005900801,0.0001549816,0.001582842,0.00003163997,0.0000462911,0.0008454939,0.0001153636,0.8221098,0.1463059,0.01796392,0.01072814,0.00005658986],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01027943,0.00007740608,0.9883127,0.00002429311,0.00001327668,0.000026284,0.00001897077,0.0004053493,0.0008423523],"genre_scores_gemma":[0.1004048,0.0001252462,0.8980581,0.00004880924,0.00001764291,0.00005290312,0.0001172311,0.00009281511,0.001082481],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002058959,"threshold_uncertainty_score":0.006887913,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01208811507005104,"score_gpt":0.2825683771573528,"score_spread":0.2704802620873017,"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."}}