{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007765145,0.00131748,0.0008268527,0.0009082214,0.0003651724,0.0006220897,0.001295841,0.001105519,0.001600035],"category_scores_gemma":[0.002450922,0.0006401355,0.0007081712,0.0005842826,0.0006530934,0.001476887,0.0009733968,0.001310797,0.0004388886],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000983462,"about_ca_system_score_gemma":0.001059824,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01087862,"about_ca_topic_score_gemma":0.01095475,"domain_scores_codex":[0.9997396,0.00005101983,0.00001229864,0.00009299393,0.00006085416,0.00004322607],"domain_scores_gemma":[0.9995315,0.0001839335,0.00007206772,0.0000607799,0.0001210062,0.00003060078],"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":[0.0001282419,0.0000786749,0.0007065019,0.0000691734,0.00005787839,0.00008301537,0.00006441106,0.7231855,0.01066257,0.00783887,0.002622967,0.2545022],"study_design_scores_gemma":[0.000003552172,0.00001005636,0.00003157309,0.00000224666,0.000002727121,0.000005147641,0.000001439954,0.9977571,0.0007869385,0.001180867,0.0002162216,0.000002152431],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02543416,0.0004422987,0.9708804,0.0001792267,0.00005760521,0.0000427302,0.00007931881,0.00156464,0.001319637],"genre_scores_gemma":[0.5521736,0.0006117062,0.4386493,0.0003062236,0.0001338918,0.0001779226,0.0008777442,0.000297134,0.006772531],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01087862,"threshold_uncertainty_score":0.02163059,"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."}}