{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001925054,0.00008500244,0.000102709,0.00006787092,0.00006999169,0.00005430033,0.0001642348,0.0000239819,0.00004758687],"category_scores_gemma":[0.00004879399,0.00007734434,0.00004691459,0.0002245244,0.0000189615,0.000748796,0.00006506487,0.00007905684,0.00006136597],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006448023,"about_ca_system_score_gemma":0.00002801261,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000792235,"about_ca_topic_score_gemma":0.00000312971,"domain_scores_codex":[0.9992262,0.00003469787,0.0001275109,0.0002667095,0.0001349241,0.0002100327],"domain_scores_gemma":[0.9994113,0.0003189417,0.00003897207,0.0001285186,0.00006589255,0.00003640968],"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":[0.00003766592,0.00004119526,0.006257796,0.00001398825,0.000008489254,0.000001216923,0.00006377346,0.6719379,0.001090596,0.01886985,0.004809494,0.296868],"study_design_scores_gemma":[0.0005681092,0.00004644202,0.02271767,0.00001436763,8.309783e-7,0.000005767695,0.000005828768,0.9675658,0.0005574627,0.007702325,0.0007165723,0.00009886819],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002888804,0.00005062874,0.9932617,0.0006394775,0.000769548,0.0004094037,0.000001941977,0.0001139949,0.001864494],"genre_scores_gemma":[0.3555123,0.000001272585,0.6432806,0.0005294342,0.00007700991,0.00005106199,0.00000815539,0.000005422125,0.0005347728],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3526235,"threshold_uncertainty_score":0.315401,"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."}}