{"id":"W2128674615","doi":"10.1109/smbv.2001.988759","title":"Multi-resolution stereo matching using genetic algorithm","year":2002,"lang":"en","type":"article","venue":"","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":37,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; University of Tsukuba; Carnegie Mellon University","keywords":"Quadtree; Computer science; Artificial intelligence; Computer vision; Matching (statistics); Pixel; Image resolution; Algorithm; Genetic algorithm; Pattern recognition (psychology); Mathematics; Machine learning","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":[0.00005271438,0.00008509355,0.00007350168,0.00007084841,0.0001398866,0.0001170999,0.0002383646,0.00001970066,0.00008561013],"category_scores_gemma":[0.000005937195,0.0000764552,0.00003202006,0.0001782603,0.00001488799,0.0005697626,0.0001741785,0.00007297413,0.0001430437],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003433089,"about_ca_system_score_gemma":0.000004533266,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002857384,"about_ca_topic_score_gemma":7.724369e-7,"domain_scores_codex":[0.9992259,0.00002578093,0.0001403367,0.0002450275,0.000143686,0.000219318],"domain_scores_gemma":[0.9995725,0.00001527363,0.00003909876,0.0002787343,0.00002845152,0.00006600846],"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":[1.748115e-7,0.0000449209,0.00004008613,0.000002961707,0.000003150191,0.0000200498,0.0004258599,0.005720472,0.003631766,0.0003197817,0.0001213551,0.9896694],"study_design_scores_gemma":[0.0001932832,0.000008064161,0.0004145215,0.00001181548,0.000001158972,0.00004948898,0.00002348937,0.9977134,0.0003307415,0.0003353921,0.0008068309,0.0001117714],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00109829,0.0002386943,0.9975531,0.0001437222,0.0002228971,0.00005654881,2.612181e-7,0.0001805151,0.0005059347],"genre_scores_gemma":[0.01815057,0.00001563062,0.9805808,0.000504402,0.00003619626,9.7944e-7,1.339878e-7,0.000006635302,0.0007046686],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.991993,"threshold_uncertainty_score":0.3117753,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05057894042988609,"score_gpt":0.2956820546528569,"score_spread":0.2451031142229708,"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."}}