{"id":"W4366425237","doi":"10.3390/s23084080","title":"Regularization for Unsupervised Learning of Optical Flow","year":2023,"lang":"en","type":"article","venue":"Sensors","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Regularization (linguistics); Computer science; Inference; Artificial intelligence; Convolutional neural network; Computation; Deep learning; Optical flow; Artificial neural network; Generalization; Machine learning; Deep neural networks; Unsupervised learning; Pattern recognition (psychology); Algorithm; Mathematics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.001291238,0.001390972,0.0008790679,0.0009441462,0.0005599305,0.0006670236,0.002144902,0.001370564,0.002229707],"category_scores_gemma":[0.00453298,0.0007314835,0.001025324,0.000890917,0.001185694,0.001600426,0.001352904,0.002642995,0.0009707073],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001274471,"about_ca_system_score_gemma":0.001892446,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006701358,"about_ca_topic_score_gemma":0.01066679,"domain_scores_codex":[0.9993956,0.0001452438,0.00002585054,0.0002104915,0.0001620416,0.00006081396],"domain_scores_gemma":[0.9988316,0.0004288587,0.0001412654,0.0002928039,0.000257871,0.00004770585],"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":[0.000122137,0.0001203143,0.001129093,0.0001665937,0.0001479615,0.00006511906,0.00008697049,0.5759594,0.02013794,0.02740297,0.01272867,0.3619328],"study_design_scores_gemma":[0.000005273228,0.00001074073,0.0001265935,0.000005266759,0.000004045897,0.00001272021,0.000002677058,0.9903418,0.002721134,0.005698791,0.001065976,0.000005003511],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004190636,0.0001371129,0.9928767,0.0001160043,0.00003103834,0.00003548522,0.00008718477,0.001732083,0.0007937329],"genre_scores_gemma":[0.2812773,0.0003887395,0.7075985,0.0004372578,0.0002016649,0.0004093748,0.00141825,0.0009398522,0.007329125],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006701358,"threshold_uncertainty_score":0.01332468,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01974733393849838,"score_gpt":0.2802751679545655,"score_spread":0.2605278340160672,"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."}}