{"id":"W2138468304","doi":"10.1109/tpami.2011.67","title":"A Component-Wise Analysis of Constructible Match Cost Functions for Global Stereopsis","year":2011,"lang":"en","type":"article","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta; University of Saskatchewan","funders":"Division of Mathematical Sciences; Natural Sciences and Engineering Research Council of Canada; Western Canada Research Grid; University of Saskatchewan","keywords":"Stereopsis; Artificial intelligence; Computer stereo vision; Computer science; Set (abstract data type); Context (archaeology); Computer vision; Smoothness; Pixel; Component (thermodynamics); Algorithm; Noise (video); Measure (data warehouse); Mathematics; Pattern recognition (psychology); Image (mathematics); Data mining","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":[0.0001770325,0.0002258472,0.0005541805,0.0008677086,0.0002133055,0.00006776993,0.0004275367,0.00005034748,0.0002565405],"category_scores_gemma":[0.000004610852,0.0002033232,0.0005880229,0.003271264,0.0001268193,0.0003099026,0.0000100267,0.0001253625,0.000008502133],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004006457,"about_ca_system_score_gemma":0.00002133773,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001142216,"about_ca_topic_score_gemma":0.001443485,"domain_scores_codex":[0.9983509,0.0000592422,0.0005379787,0.0005616939,0.0002312099,0.0002589329],"domain_scores_gemma":[0.9987226,0.0001298122,0.0002096112,0.0005986584,0.0001808054,0.0001585745],"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":[0.0000416897,0.000333077,0.01027327,0.00001961772,0.003811056,0.000002734283,0.000412785,0.01043301,0.0001878426,0.0005011649,0.000007288858,0.9739764],"study_design_scores_gemma":[0.0002792555,0.0001845109,0.009828411,0.0000244562,0.005859267,0.00001096514,0.0003113516,0.9471409,0.03517485,0.0006865404,0.0001095539,0.0003899066],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003707336,0.00005752124,0.9951591,0.00009439234,0.0001929236,0.0002083902,0.0003118231,0.00006788165,0.0002005716],"genre_scores_gemma":[0.9740543,0.00009855921,0.02546485,0.0002171147,0.000005090692,0.00003751708,0.00001324347,0.000007101994,0.000102182],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9735866,"threshold_uncertainty_score":0.8291279,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03849861319294141,"score_gpt":0.2980666341700721,"score_spread":0.2595680209771307,"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."}}