{"id":"W2895813988","doi":"10.1007/s00521-018-3816-3","title":"A CNNs-based method for optical flow estimation with prior constraints and stacked U-Nets","year":2018,"lang":"en","type":"article","venue":"Neural Computing and Applications","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"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; Smoothness; Optical flow; Artificial neural network; Process (computing); Convolution (computer science); Function (biology); Algorithm; Flow (mathematics); Artificial intelligence; Deep learning; Machine learning; Mathematical optimization; 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":[0.0001437216,0.0000929399,0.0001029762,0.00004196584,0.000391714,0.00013119,0.0001271844,0.00002170125,0.000001033271],"category_scores_gemma":[0.00002946855,0.0000767842,0.00001412411,0.000152634,0.0001795327,0.0001177401,0.00006085906,0.00006758355,0.000001793035],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000007316401,"about_ca_system_score_gemma":0.0000270299,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001280307,"about_ca_topic_score_gemma":8.943691e-7,"domain_scores_codex":[0.9992797,0.0000181407,0.0001284701,0.000331112,0.00008204857,0.0001605755],"domain_scores_gemma":[0.9992662,0.0002984836,0.00005892067,0.0001829091,0.0001041086,0.00008938182],"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":[0.000005747577,0.00001563801,0.00003516886,0.00001070335,0.000002265513,2.144924e-7,0.00007222636,0.000600867,0.0006264059,0.00787471,0.00002834369,0.9907277],"study_design_scores_gemma":[0.0004892574,0.0001160225,0.0006035495,0.00002041593,0.000006083926,0.00002452038,0.00001385815,0.994572,0.001475832,0.001516132,0.00106167,0.0001006369],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004649119,0.00001727016,0.9930744,0.001604754,0.00002062508,0.0003857059,0.000003013612,0.0001307527,0.0001143593],"genre_scores_gemma":[0.3511282,3.532794e-7,0.6483664,0.0004396641,0.00003166187,0.0000210213,0.000002966928,0.000004256874,0.000005504126],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9939712,"threshold_uncertainty_score":0.3131169,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01930222214713203,"score_gpt":0.3465273953366105,"score_spread":0.3272251731894785,"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."}}