{"id":"W2567216070","doi":"10.1109/crv.2016.60","title":"Hierarchical Grouping Approach for Fast Approximate RGB-D Scene Flow","year":2016,"lang":"en","type":"article","venue":"","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Optical flow; RGB color model; Computer science; Artificial intelligence; Computer vision; Flow (mathematics); Set (abstract data type); Matching (statistics); Motion (physics); Object (grammar); Pattern recognition (psychology); 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000219238,0.0001287896,0.0001454973,0.00007773807,0.0001470087,0.000104631,0.0006383838,0.00003312624,0.00001756005],"category_scores_gemma":[0.00005708889,0.0000763923,0.00007683552,0.0001662283,0.00005413622,0.0007094087,0.0002887668,0.00006475765,0.00002648061],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002730345,"about_ca_system_score_gemma":0.00002183657,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":8.307488e-7,"about_ca_topic_score_gemma":1.493105e-7,"domain_scores_codex":[0.9987532,0.00002411235,0.0001838451,0.000470766,0.0001771145,0.0003909487],"domain_scores_gemma":[0.9992413,0.0001029515,0.00003989241,0.0004350956,0.00005182243,0.0001289452],"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":[0.00000678442,0.00004148902,0.00003621401,0.00001244126,0.000004106853,8.375436e-7,0.00006824992,0.00002396909,0.004586799,0.04979641,0.0005147148,0.944908],"study_design_scores_gemma":[0.0006522968,0.00003573961,0.00006852533,0.00002185171,0.000001318443,0.00001207262,0.00001346949,0.9812621,0.003828241,0.009383361,0.004542745,0.0001783204],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00005277734,0.00002567759,0.9898236,0.001793791,0.0001478475,0.0002081584,0.000002129896,0.0003032883,0.007642662],"genre_scores_gemma":[0.03585339,0.000007917604,0.9618818,0.0007509983,0.00009148682,0.00003670563,0.000001841025,0.00001225064,0.001363665],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9812381,"threshold_uncertainty_score":0.3115188,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02253797490461365,"score_gpt":0.270536955526206,"score_spread":0.2479989806215924,"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."}}