{"id":"W2017204914","doi":"10.1109/ism.2012.46","title":"Mutual Information Based Stereo Correspondence in Extreme Cases","year":2012,"lang":"en","type":"article","venue":"","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Mutual information; Markov random field; Computer science; Artificial intelligence; Ambiguity; Context (archaeology); Markov chain; Matching (statistics); Term (time); Markov process; Pattern recognition (psychology); Computer vision; Mathematics; Image (mathematics); Machine learning; Image segmentation; Statistics; Geography","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":[0.0001854415,0.00006032855,0.00005529655,0.0001461965,0.00003268692,0.00006828689,0.0002409078,0.00001575397,0.0001194817],"category_scores_gemma":[0.0001037581,0.00005079288,0.00001506763,0.0002707196,0.00001278105,0.00472565,0.00008778502,0.00005901679,0.0003652151],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002909443,"about_ca_system_score_gemma":0.00002819696,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001595018,"about_ca_topic_score_gemma":0.000005205907,"domain_scores_codex":[0.9993905,0.0000276009,0.0001489944,0.00007263405,0.0001541086,0.0002061886],"domain_scores_gemma":[0.9995442,0.0001108913,0.00003759297,0.0002104364,0.00002797136,0.00006892866],"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":[0.00002704237,0.00009672556,0.03349734,0.00001222337,0.000001125486,0.00001349084,0.001873683,0.0002319904,0.0006665743,0.02293221,0.002862604,0.937785],"study_design_scores_gemma":[0.0005819503,0.00004384285,0.03020272,0.00003231291,7.119749e-7,0.00004008331,0.0003045129,0.9251578,0.00334664,0.0001383748,0.03992363,0.0002274034],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01664565,0.00002940086,0.9776376,0.0002378865,0.0002549323,0.00006069093,4.226901e-7,0.00008963366,0.005043766],"genre_scores_gemma":[0.8975545,0.000001143928,0.1003089,0.001844842,0.00001416292,0.000003548718,0.000001179619,0.000001526028,0.000270167],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9375576,"threshold_uncertainty_score":0.4694224,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07993111315244605,"score_gpt":0.2890484060172989,"score_spread":0.2091172928648529,"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."}}