{"id":"W2963652593","doi":"10.1109/cvpr.2019.00373","title":"Deep Rigid Instance Scene Flow","year":2019,"lang":"en","type":"article","venue":"","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":133,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Artificial intelligence; Leverage (statistics); Computer vision; Prior probability; Solver; Margin (machine learning); Optical flow; Deep learning; Gaussian; Minification; Context (archaeology); Energy minimization; Flow (mathematics); Domain (mathematical analysis); Machine learning; Image (mathematics); Mathematics; Bayesian probability","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":[0.0005789574,0.001533728,0.00129662,0.001129533,0.0005274528,0.001406715,0.002121079,0.001786019,0.005764476],"category_scores_gemma":[0.00148632,0.0006782939,0.001181034,0.00111783,0.0006634833,0.002375885,0.001609638,0.002384427,0.001903795],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001028396,"about_ca_system_score_gemma":0.00140423,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007757229,"about_ca_topic_score_gemma":0.009564226,"domain_scores_codex":[0.9995779,0.00005758613,0.00001330939,0.0001571976,0.0001190815,0.00007489798],"domain_scores_gemma":[0.9996713,0.00008190668,0.00003758009,0.0001045415,0.00006791623,0.00003681241],"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":[0.0002030149,0.0002117435,0.000992137,0.0001628694,0.0001060186,0.000137349,0.00009444264,0.519479,0.01423578,0.04677748,0.02043905,0.3971612],"study_design_scores_gemma":[0.000005960075,0.000017567,0.0001077127,0.000005916672,0.00000467479,0.00003389874,0.000006496899,0.9862421,0.002183205,0.008443645,0.002942871,0.000006119731],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008645193,0.0003123226,0.984785,0.0002358378,0.000102477,0.00006567943,0.0005467311,0.00327911,0.002027761],"genre_scores_gemma":[0.3390551,0.0006739885,0.64024,0.0004335554,0.0002446133,0.0001544791,0.006111141,0.001141334,0.01194579],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007757229,"threshold_uncertainty_score":0.01928413,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006190316035183527,"score_gpt":0.2394190156872911,"score_spread":0.2332286996521076,"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."}}