{"id":"W3183877130","doi":"10.1109/wacv51458.2022.00403","title":"Detail Preserving Residual Feature Pyramid Modules for Optical Flow","year":2022,"lang":"en","type":"article","venue":"2022 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Upsampling; Pyramid (geometry); Feature (linguistics); Computer science; Residual; Modular design; Artificial intelligence; Optical flow; Feature extraction; Iterative method; Flow (mathematics); Computer vision; Pattern recognition (psychology); Algorithm; 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":[0.0007425323,0.0008946541,0.0005172219,0.0007857816,0.0003392892,0.0004964231,0.001481291,0.0006732037,0.003570132],"category_scores_gemma":[0.001823719,0.0004068902,0.0007825732,0.0008213229,0.0003811627,0.001562636,0.001070506,0.001173207,0.00135934],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005325266,"about_ca_system_score_gemma":0.00095351,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004093451,"about_ca_topic_score_gemma":0.005616826,"domain_scores_codex":[0.9996582,0.00004324379,0.00001526565,0.00007835593,0.0001562353,0.00004870504],"domain_scores_gemma":[0.9994572,0.0001156457,0.00005297244,0.0001793272,0.0001608034,0.0000339746],"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":[0.000176128,0.0001521822,0.0007474629,0.0001159669,0.00007971447,0.00006013647,0.00008820609,0.1149206,0.1055723,0.008006933,0.005777477,0.7643028],"study_design_scores_gemma":[0.0000199643,0.0001414201,0.0007363768,0.00001056581,0.0000212541,0.00008412655,0.000009500218,0.9491523,0.04104282,0.004132936,0.004626244,0.00002251544],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008211757,0.00009355337,0.9887693,0.00004528041,0.00001868428,0.00004063016,0.00006134771,0.002047774,0.0007116867],"genre_scores_gemma":[0.170972,0.0001502032,0.8254552,0.00009904063,0.00004263261,0.0001058626,0.0005484233,0.0003108878,0.002315736],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004093451,"threshold_uncertainty_score":0.01194328,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02115698958245709,"score_gpt":0.2993427656259109,"score_spread":0.2781857760434538,"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."}}