{"id":"W2157507035","doi":"10.1109/icip.2002.1039102","title":"Reliability measurement of disparity estimates for intermediate view reconstruction","year":2003,"lang":"en","type":"article","venue":"Proceedings - International Conference on Image Processing","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"Communications Research Centre Canada","funders":"","keywords":"Reliability (semiconductor); Artificial intelligence; Computer science; Stereoscopy; A priori and a posteriori; Iterative reconstruction; Image (mathematics); Computer vision; Quality (philosophy); Stereopsis; Image quality; Algorithm","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":[0.0008278582,0.0001943955,0.0002344088,0.0001563599,0.0001453716,0.0003757908,0.0006079716,0.00004347387,0.00003542986],"category_scores_gemma":[0.001882737,0.0001760222,0.00007626005,0.0001998781,0.0001143757,0.002004822,0.00009054694,0.0001690159,0.000005494933],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001502364,"about_ca_system_score_gemma":0.0001611551,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002367929,"about_ca_topic_score_gemma":6.272434e-7,"domain_scores_codex":[0.9982084,0.00001179338,0.0004713531,0.0005268227,0.0005385702,0.0002430731],"domain_scores_gemma":[0.9966097,0.00004226397,0.0004156498,0.0001287487,0.002722018,0.00008164981],"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":[0.0000853622,0.0002732779,0.002441159,0.0006434409,0.00003441358,7.292994e-7,0.000647405,0.00001101494,0.1016307,0.1797355,0.0001288938,0.7143681],"study_design_scores_gemma":[0.001003784,0.0001687634,0.001900238,0.001671732,0.00002170128,0.00003700153,0.0003338663,0.6406534,0.1808212,0.1718899,0.001038571,0.0004598118],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005559632,0.0001199188,0.9788671,0.0007910948,0.0005329628,0.0003184022,0.000004679715,0.0001356232,0.01367057],"genre_scores_gemma":[0.7094179,0.00003055025,0.2903653,0.0000791329,0.00002525316,0.00005253049,0.000001321412,0.000008795316,0.00001913099],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7139083,"threshold_uncertainty_score":0.7177977,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05348686654118301,"score_gpt":0.3311693673590731,"score_spread":0.2776825008178901,"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."}}