{"id":"W2888898946","doi":"10.1109/access.2018.2863233","title":"Deep Optical Flow Supervised Learning With Prior Assumptions","year":2018,"lang":"en","type":"article","venue":"IEEE Access","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":16,"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":"Optical flow; Computer science; Smoothness; Ground truth; Artificial intelligence; Convolutional neural network; Flow (mathematics); Brightness; Machine learning; Artificial neural network; Deep learning; Pattern recognition (psychology); Computer vision; Algorithm; Image (mathematics); Mathematics; Optics","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":[0.0001055138,0.0001083673,0.0001107687,0.00007951046,0.0003127346,0.0004339558,0.0009167169,0.00002919041,0.00008177783],"category_scores_gemma":[0.00004348642,0.00008501616,0.00002823788,0.000370414,0.00009849825,0.001612397,0.0001940909,0.000180693,0.000236202],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002179798,"about_ca_system_score_gemma":0.00003837919,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004462639,"about_ca_topic_score_gemma":0.00001290209,"domain_scores_codex":[0.998992,0.000032771,0.000125659,0.0003343382,0.0002329119,0.0002823385],"domain_scores_gemma":[0.9992687,0.00006442839,0.00003811219,0.0003673946,0.0001430712,0.0001183178],"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":[0.00002513002,0.00009856294,0.005676175,0.000013249,0.00002054536,0.00004045496,0.0009184775,0.004266834,0.003108427,0.002508345,0.0005613791,0.9827624],"study_design_scores_gemma":[0.0004761911,0.0001200947,0.006239965,0.00003439355,0.000005476578,0.0000255775,0.00002350693,0.9779614,0.009482001,0.0004383312,0.004981753,0.0002113329],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02263638,0.00001941052,0.9728945,0.0005768103,0.0003185356,0.00008158268,1.488976e-7,0.0002369702,0.003235698],"genre_scores_gemma":[0.7049814,0.000006091832,0.2940292,0.0005538479,0.000183827,0.000008702451,7.368081e-7,0.00001136816,0.000224844],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9825511,"threshold_uncertainty_score":0.4184646,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02780662459410874,"score_gpt":0.3236465253519578,"score_spread":0.295839900757849,"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."}}