{"id":"W2982688687","doi":"10.1109/3dv.2019.00079","title":"Effective Convolutional Neural Network Layers in Flow Estimation for Omni-Directional Images","year":2019,"lang":"en","type":"article","venue":"","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Optical flow; Computer science; Convolutional neural network; Artificial intelligence; Artificial neural network; Convolution (computer science); Computer vision; Flow (mathematics); Optical computing; Computer graphics; Planar; Image (mathematics); Computer graphics (images); Electronic engineering","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":[0.001976535,0.001162928,0.0005387538,0.001174683,0.0004083922,0.0008989855,0.001050397,0.001185733,0.001591905],"category_scores_gemma":[0.004738642,0.000432802,0.000570865,0.000818527,0.0005605016,0.001882488,0.0006762801,0.001170747,0.0004093307],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001154277,"about_ca_system_score_gemma":0.001073675,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01211517,"about_ca_topic_score_gemma":0.01469036,"domain_scores_codex":[0.999513,0.0001023556,0.00002527762,0.0001378385,0.0001163097,0.0001051888],"domain_scores_gemma":[0.9992443,0.000341314,0.00009055268,0.0001144252,0.0001647925,0.00004463683],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0004768866,0.0002341104,0.004313902,0.0001650202,0.0001289559,0.0001365368,0.00005405072,0.6198005,0.02331884,0.006810224,0.003084291,0.3414767],"study_design_scores_gemma":[0.000008014901,0.00003443773,0.0006428005,0.00001080165,0.00001319932,0.00002565422,0.0000074036,0.9901205,0.007107656,0.001504097,0.0005186219,0.000006775962],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2189531,0.002130183,0.7702486,0.0005767781,0.0001555755,0.0001331324,0.0008580463,0.00255882,0.004385737],"genre_scores_gemma":[0.7049918,0.0006640612,0.2895307,0.0002207472,0.00006141246,0.00009681818,0.001212808,0.0001683977,0.003053315],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01211517,"threshold_uncertainty_score":0.02408934,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006096473442340048,"score_gpt":0.2663516371558338,"score_spread":0.2602551637134938,"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."}}