{"id":"W2950291510","doi":"10.48550/arxiv.1604.01827","title":"Exploiting Semantic Information and Deep Matching for Optical Flow","year":2016,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Optical flow; Computer science; Epipolar geometry; Margin (machine learning); Artificial intelligence; Benchmark (surveying); Matching (statistics); Context (archaeology); Pipeline (software); Segmentation; Computer vision; Monocular; Flow (mathematics); Traffic flow (computer networking); Machine learning; 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":[0.0009987563,0.001646015,0.001190535,0.002765667,0.000735405,0.001464784,0.001853674,0.001945291,0.001984223],"category_scores_gemma":[0.003033083,0.0006679941,0.0009257901,0.002123414,0.001027038,0.003547705,0.002138408,0.002061006,0.0008568158],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001311843,"about_ca_system_score_gemma":0.001635832,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01040073,"about_ca_topic_score_gemma":0.01071624,"domain_scores_codex":[0.9993575,0.00008010084,0.00002734048,0.0002280612,0.0001778994,0.0001292027],"domain_scores_gemma":[0.9993502,0.000148466,0.0001291884,0.0001744467,0.0001474883,0.00005016458],"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":[0.0002545543,0.0003052549,0.002094933,0.0001517336,0.0001055631,0.0001007809,0.0001087133,0.3589774,0.0265184,0.03021303,0.005973862,0.5751957],"study_design_scores_gemma":[0.000006116074,0.00002434604,0.0002714551,0.000008998065,0.000008635664,0.00002342886,0.000008154528,0.9788315,0.004410948,0.0154538,0.0009440222,0.000008581742],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02253566,0.0002494255,0.9739369,0.0002025896,0.00005865661,0.00003768575,0.0001836873,0.001454235,0.001341172],"genre_scores_gemma":[0.6034695,0.0004991597,0.3900081,0.0002933161,0.0002340286,0.00007856902,0.001492479,0.0003075043,0.003617377],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01040073,"threshold_uncertainty_score":0.02068043,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04301496973351364,"score_gpt":0.200837653869035,"score_spread":0.1578226841355214,"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."}}