{"id":"W2128684834","doi":"10.1109/tpami.2005.120","title":"Fast unambiguous stereo matching using reliability-based dynamic programming","year":2005,"lang":"en","type":"article","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":70,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta; Laurentian University","funders":"","keywords":"Pixel; Reliability (semiconductor); Dynamic programming; Matching (statistics); Computer science; Artificial intelligence; Scan line; Stereopsis; Computer vision; Image (mathematics); Algorithm; Mathematics; Statistics","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002856334,0.0002766019,0.0003353989,0.0005975312,0.0003685605,0.0002714882,0.0004629903,0.00005340889,0.00006059166],"category_scores_gemma":[0.000003176733,0.0002496147,0.0002705087,0.001155599,0.00007351951,0.000545253,0.000009799673,0.0003586308,0.00002126548],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001078849,"about_ca_system_score_gemma":0.00002890572,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005459127,"about_ca_topic_score_gemma":0.0005787853,"domain_scores_codex":[0.9980392,0.00009590252,0.0004757491,0.0007104077,0.0003215107,0.0003572377],"domain_scores_gemma":[0.9988764,0.00009587696,0.0001386169,0.0006462429,0.0000805637,0.0001623134],"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":[0.000003643317,0.0001094251,0.0001503067,0.00001109172,0.00005473277,0.000003949765,0.000195865,0.3044159,0.0004236649,0.000007015234,1.318258e-7,0.6946242],"study_design_scores_gemma":[0.0001027752,0.00005005099,0.0001423742,0.0000444469,0.0001567503,0.00001129361,0.00006713836,0.9741263,0.02481931,0.0001199094,0.00008140413,0.0002781826],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01404525,0.0000764783,0.9848725,0.0005306533,0.0001270999,0.0001445973,0.00001130419,0.0001757724,0.00001636887],"genre_scores_gemma":[0.8458477,0.00003913625,0.1533982,0.0006137551,0.0000114704,0.000009820309,0.000002444328,0.00001487611,0.00006262183],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8318024,"threshold_uncertainty_score":0.9999956,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01699624700071466,"score_gpt":0.2995241662770096,"score_spread":0.2825279192762949,"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."}}