{"id":"W2469078500","doi":"10.5194/isprs-annals-iii-3-123-2016","title":"REVISITING INTRINSIC CURVES FOR EFFICIENT DENSE STEREO MATCHING","year":2016,"lang":"en","type":"article","venue":"ISPRS annals of the photogrammetry, remote sensing and spatial information sciences","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"Centre de Géomatique du Québec; York University; Université de Sherbrooke","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Artificial intelligence; Pixel; Computer vision; Computer science; Matching (statistics); Regularization (linguistics); Ambiguity; Photogrammetry; Mathematics; Pattern recognition (psychology)","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":[0.001473193,0.0001322483,0.0001924267,0.0001943974,0.0004855565,0.0002594228,0.0004629488,0.00002908637,0.00000122375],"category_scores_gemma":[0.0007314402,0.00007347231,0.0001073575,0.0005530593,0.0002390932,0.0006117472,0.0002672876,0.00006474504,0.000002406204],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001040367,"about_ca_system_score_gemma":0.00005030037,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004443711,"about_ca_topic_score_gemma":0.0001241338,"domain_scores_codex":[0.9985152,0.00007223938,0.0004710022,0.0002045131,0.000426399,0.0003106103],"domain_scores_gemma":[0.9985354,0.000319995,0.0004539555,0.0003025673,0.0003092608,0.00007880865],"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":[0.000005785734,0.000002492349,0.00001669565,0.00004565237,0.000003581424,9.927586e-8,0.00031829,0.0001033133,0.00103877,0.00006711184,0.00009543222,0.9983028],"study_design_scores_gemma":[0.0002499577,0.00006329281,0.0004406755,0.001218279,0.000004874295,0.00002251891,0.0002070099,0.9628907,0.02865213,0.002836259,0.003241986,0.0001723166],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01501864,0.0001664956,0.9747486,0.009181031,0.0003481746,0.0002562743,0.000005025416,0.00004963546,0.0002261175],"genre_scores_gemma":[0.963903,0.0001913453,0.03330549,0.002544549,0.00003368628,2.134841e-7,4.569177e-7,0.000003666769,0.00001760534],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9981304,"threshold_uncertainty_score":0.6717591,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04343993242007997,"score_gpt":0.3239632465355918,"score_spread":0.2805233141155118,"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."}}