{"id":"W2157431410","doi":"10.1007/s11263-006-0032-x","title":"A Performance Study on Different Cost Aggregation Approaches Used in Real-Time Stereo Matching","year":2007,"lang":"en","type":"article","venue":"International Journal of Computer Vision","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":176,"is_retracted":false,"has_abstract":false,"ca_institutions":"Laurentian University; University of Calgary","funders":"National Science Council; University of Kentucky; National Science Foundation","keywords":"Computer science; Graphics; Matching (statistics); Constraint (computer-aided design); Artificial intelligence; Computation; Process (computing); Time constraint; Pixel; Stereopsis; Speedup; Computer graphics; Computer vision; Algorithm; Computer graphics (images); Mathematics; Parallel computing","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":[0.000950411,0.0001633194,0.0002318759,0.0006691094,0.00005317908,0.0002287498,0.001027282,0.00003321609,0.000005751695],"category_scores_gemma":[0.00001374564,0.0001279687,0.00008189725,0.0001892549,0.00001685584,0.001157407,0.0002576224,0.0002805591,0.00001885019],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002189162,"about_ca_system_score_gemma":0.00002643989,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004142743,"about_ca_topic_score_gemma":0.000003514443,"domain_scores_codex":[0.9977991,0.00009475016,0.000697298,0.000242472,0.0009700462,0.0001963552],"domain_scores_gemma":[0.9988173,0.0002224329,0.0004516095,0.0002129061,0.0002051344,0.0000906552],"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":[0.0002433693,0.001004783,0.02070623,0.000004390986,0.00003872138,0.0002223398,0.002852048,0.006038995,0.002421679,0.0004023959,0.00004939979,0.9660156],"study_design_scores_gemma":[0.002803778,0.001267089,0.4462259,0.0006112256,0.000004293806,0.0001685785,0.0001511546,0.5453936,0.002453781,0.0005538317,0.0001410514,0.000225682],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.559342,0.000004278115,0.4395446,0.000210538,0.0006196883,0.000109417,2.214647e-7,0.00001802029,0.0001512236],"genre_scores_gemma":[0.9703385,0.00001231455,0.02923848,0.0001057081,0.0002705891,0.000001185357,0.000001414023,0.000009921167,0.00002189923],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.96579,"threshold_uncertainty_score":0.5218412,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03976144217590096,"score_gpt":0.3290448712590217,"score_spread":0.2892834290831208,"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."}}