{"id":"W2184426797","doi":"10.20385/1860-2037/9.2012.4","title":"Sharpness Matching in Stereo Images","year":2010,"lang":"en","type":"article","venue":"Hochschule Düsseldorf","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Artificial intelligence; Computer vision; Discrete cosine transform; Brightness; Computer stereo vision; Matching (statistics); Computer science; Image (mathematics); Mathematics; Stereo image; Stereopsis; Pattern recognition (psychology); Optics","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":[0.000298319,0.0001555265,0.0001699614,0.000177829,0.0001118096,0.0002402887,0.0009361397,0.00005648631,0.00009589146],"category_scores_gemma":[0.00005987864,0.0001460602,0.00004984481,0.0003975001,0.0000388868,0.001263578,0.0003421164,0.0004893098,0.0002194813],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001647638,"about_ca_system_score_gemma":0.00003863141,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004828794,"about_ca_topic_score_gemma":0.00006274854,"domain_scores_codex":[0.9987038,0.00003489563,0.0002393918,0.0004242987,0.0002190203,0.0003785736],"domain_scores_gemma":[0.9990348,0.00008200755,0.00006711739,0.0006572512,0.00004868257,0.0001101804],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0000162728,0.0002908903,0.01036498,0.00005989884,0.00001139655,0.0002754219,0.003102525,0.0001430186,0.2644342,0.1172313,0.002516503,0.6015537],"study_design_scores_gemma":[0.006176823,0.0002403229,0.260855,0.0005245088,0.00001647355,0.0006012525,0.001296005,0.1967119,0.188645,0.2378244,0.1031754,0.003933033],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2759977,0.0001312407,0.6998267,0.002067395,0.001516434,0.0002060585,0.000003227452,0.0004329543,0.01981827],"genre_scores_gemma":[0.8581113,0.00001065967,0.1405189,0.0007148728,0.00008449599,0.00001208534,0.000001789371,0.00001464485,0.0005312521],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5976207,"threshold_uncertainty_score":0.5956162,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006839829390956273,"score_gpt":0.26844547859941,"score_spread":0.2616056492084537,"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."}}