{"id":"W2440384215","doi":"10.1109/cvpr.2016.614","title":"Efficient Deep Learning for Stereo Matching","year":2016,"lang":"en","type":"article","venue":"","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":803,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Exploit; Computer science; Concatenation (mathematics); Computation; Matching (statistics); Convolutional neural network; Artificial intelligence; Product (mathematics); Layer (electronics); Class (philosophy); Artificial neural network; Pattern recognition (psychology); Algorithm; Mathematics; Arithmetic","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004797045,0.0006196187,0.0006837738,0.0007303882,0.0003641904,0.0006561605,0.001184889,0.0009478967,0.006998813],"category_scores_gemma":[0.001410619,0.0004340683,0.0004610215,0.001127428,0.000413814,0.001260725,0.001285912,0.001095456,0.001940841],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00110501,"about_ca_system_score_gemma":0.001029177,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005572184,"about_ca_topic_score_gemma":0.009904473,"domain_scores_codex":[0.9996641,0.00004139322,0.00001390579,0.00007258006,0.0001541684,0.00005384354],"domain_scores_gemma":[0.9997651,0.00006513354,0.00002454646,0.00006230896,0.00006467433,0.00001815665],"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":[0.0001689082,0.00008946597,0.000597499,0.0001111826,0.00006011796,0.00006689198,0.00004675718,0.2884496,0.02088399,0.02526382,0.008389915,0.6558718],"study_design_scores_gemma":[0.000006869062,0.00001321225,0.0001029287,0.000004637523,0.000003692053,0.00002084848,0.000005290756,0.9854951,0.003508738,0.009110749,0.001724036,0.000003918755],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01028673,0.0004505894,0.984553,0.0001660304,0.00004312027,0.00003183664,0.0001607346,0.001587244,0.002720763],"genre_scores_gemma":[0.38915,0.0005886159,0.6003036,0.0002722354,0.00008743107,0.0001300583,0.0008904329,0.0003116885,0.008265967],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006998813,"threshold_uncertainty_score":0.02341336,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01328755608136784,"score_gpt":0.2795611911963601,"score_spread":0.2662736351149922,"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."}}