{"id":"W4386171497","doi":"10.1016/j.patcog.2023.109918","title":"InvFlow: Involution and multi-scale interaction for unsupervised learning of optical flow","year":2023,"lang":"en","type":"article","venue":"Pattern Recognition","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Optical flow; Convolution (computer science); Artificial intelligence; Encoder; Convolutional neural network; Artificial neural network; Pattern recognition (psychology); Feature (linguistics); Computer vision; Image (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":[0.001901464,0.001168918,0.001168394,0.001233917,0.0008871935,0.001386378,0.002652018,0.001728249,0.004437096],"category_scores_gemma":[0.005369453,0.0007834686,0.001524476,0.001129716,0.00155798,0.002586604,0.003856501,0.003053544,0.001653461],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009170526,"about_ca_system_score_gemma":0.001342329,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004105121,"about_ca_topic_score_gemma":0.005952307,"domain_scores_codex":[0.9991435,0.0002308244,0.00004385161,0.0002257452,0.0002702835,0.00008581064],"domain_scores_gemma":[0.9981939,0.000842167,0.0001449098,0.0004599593,0.0002286992,0.0001302989],"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":[0.0005446766,0.000311483,0.001022823,0.0001841511,0.0001436344,0.0001541892,0.0002570528,0.2008745,0.02695391,0.05904143,0.01768064,0.6928315],"study_design_scores_gemma":[0.000008331234,0.00001997359,0.00007108344,0.000004334067,0.000003635776,0.00002018865,0.000005365504,0.9826342,0.004357475,0.01143906,0.001427544,0.000008759032],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002307587,0.00003039075,0.9944477,0.00005326016,0.00002458469,0.0000178421,0.00005661837,0.002860493,0.0002014543],"genre_scores_gemma":[0.160454,0.0001787151,0.8301982,0.0002028659,0.0001391514,0.0002987255,0.001127371,0.002789824,0.004611253],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004437096,"threshold_uncertainty_score":0.01484352,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06289675201136713,"score_gpt":0.3144779288684079,"score_spread":0.2515811768570407,"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."}}