{"id":"W2914664021","doi":"10.1109/access.2019.2898988","title":"Learning Optical Flow Using Deep Dilated Residual Networks","year":2019,"lang":"en","type":"article","venue":"IEEE Access","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"Fundamental Research Funds for the Central Universities; Natural Science Foundation of Heilongjiang Province; National Natural Science Foundation of China","keywords":"Computer science; Residual; Optical flow; Artificial intelligence; Deconvolution; Feature (linguistics); Deep learning; Network architecture; Algorithm; Smoothness; Encoder; Artificial neural network; Computer vision; Pattern recognition (psychology); Image (mathematics); Mathematics","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":[0.0001724183,0.0001239963,0.0001542062,0.00007872499,0.0001438938,0.0004554756,0.000937418,0.00005801693,0.0000461009],"category_scores_gemma":[0.00003645211,0.0001143497,0.0000398044,0.0004146381,0.00002640101,0.001640628,0.0003695303,0.0003334998,0.0000879988],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003341939,"about_ca_system_score_gemma":0.00002712775,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007684058,"about_ca_topic_score_gemma":0.000001178344,"domain_scores_codex":[0.998793,0.0000533222,0.0001855022,0.0003785134,0.0002273988,0.0003622548],"domain_scores_gemma":[0.9992952,0.0001007314,0.00006987169,0.0003670826,0.00006912494,0.00009803208],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000009152691,0.00001870341,0.005184394,0.000006254139,0.000008782508,0.00002658169,0.0001316753,0.8033732,0.00208686,0.0003984854,0.0001079554,0.1886479],"study_design_scores_gemma":[0.0002441256,0.00002579016,0.001519671,0.00003381033,0.000002992261,0.00001503406,0.00001065844,0.9949833,0.002245907,0.0002365591,0.0005132103,0.0001689393],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1107157,0.00006798177,0.8867156,0.0001130075,0.0009164871,0.00008572145,7.934606e-8,0.0001853693,0.001200096],"genre_scores_gemma":[0.9168545,0.00001074814,0.08237608,0.0004089666,0.0001593121,0.000001461577,0.000001177875,0.00001519304,0.0001725322],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8061389,"threshold_uncertainty_score":0.4663045,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0224209462941111,"score_gpt":0.3163956498737732,"score_spread":0.2939747035796621,"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."}}