{"id":"W7231517","doi":"10.1007/978-3-642-16259-6_10","title":"Performance of MRF-Based Stereo Algorithms for Cluttered Scenes","year":2010,"lang":"en","type":"book-chapter","venue":"Advances in intelligent and soft computing","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University","funders":"","keywords":"Belief propagation; Markov random field; Artificial intelligence; Computer science; Computer vision; Inpainting; Ground truth; Clutter; Algorithm; Pattern recognition (psychology); Image (mathematics); Image segmentation; Radar","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":[0.000347028,0.000375252,0.0005558345,0.0003122295,0.0001576962,0.0000660182,0.0007125724,0.0001687294,0.000009717441],"category_scores_gemma":[0.00005620629,0.0003604283,0.0001334114,0.00007968846,0.0001911215,0.0004574882,0.0003172365,0.0004533909,0.000004205741],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003508584,"about_ca_system_score_gemma":0.00006066692,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001601744,"about_ca_topic_score_gemma":0.000006086809,"domain_scores_codex":[0.9979764,0.00001324719,0.0007244399,0.0006546548,0.0002639655,0.0003672444],"domain_scores_gemma":[0.9982269,0.0005546199,0.000486006,0.0004530771,0.0001957892,0.00008357633],"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":[0.0000200346,0.00001853953,0.0004678825,0.0002633242,0.000008128262,0.000002891553,0.0001815317,0.001322293,0.00008478142,0.008618127,0.000004480021,0.989008],"study_design_scores_gemma":[0.0004839067,0.0002013545,0.0000327136,0.001441165,0.00001105332,0.000009090121,0.00002086753,0.8926085,0.004941221,0.01045574,0.08921293,0.0005814313],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0007195709,0.003523109,0.9885966,0.00007902188,0.001072471,0.0003995098,0.000006938399,0.00008348627,0.005519266],"genre_scores_gemma":[0.08026099,0.002400661,0.9110667,0.0004114476,0.000337187,0.00001356107,0.00002352442,0.00008106349,0.005404836],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9884266,"threshold_uncertainty_score":0.9998848,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02631355538188578,"score_gpt":0.3020018838749114,"score_spread":0.2756883284930257,"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."}}