{"id":"W3152200872","doi":"10.1109/iccv.2003.1238470","title":"Bayesian clustering of optical flow fields","year":2003,"lang":"en","type":"article","venue":"","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Optical flow; Probabilistic logic; A priori and a posteriori; Cluster analysis; Computer science; Artificial intelligence; Mixture model; Flow (mathematics); Pattern recognition (psychology); Set (abstract data type); Feature (linguistics); Unsupervised learning; Bayesian probability; Cluster (spacecraft); Mathematics; 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":[0.002032405,0.001314931,0.001359655,0.00424933,0.00134257,0.001531844,0.002448355,0.001748947,0.001609314],"category_scores_gemma":[0.00718664,0.001219153,0.001712801,0.002691168,0.001537826,0.002311069,0.001691294,0.001979989,0.001023728],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001816908,"about_ca_system_score_gemma":0.001868922,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01051103,"about_ca_topic_score_gemma":0.01209784,"domain_scores_codex":[0.9980317,0.0004932209,0.00008458462,0.0006203473,0.0006117387,0.000158413],"domain_scores_gemma":[0.998027,0.0005579964,0.0003494243,0.0004118819,0.0005563537,0.00009728337],"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":[0.0001841147,0.0001574132,0.002602214,0.0002140647,0.000207885,0.00008513343,0.0003654019,0.5132869,0.01102841,0.08711008,0.006807551,0.3779507],"study_design_scores_gemma":[0.00001314146,0.00002220962,0.0008925025,0.00002820198,0.00001576225,0.00005049762,0.00002486598,0.9511385,0.002178987,0.04285899,0.002739188,0.00003715536],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003545765,0.000109693,0.9953681,0.00005637366,0.00001390961,0.00003759254,0.00007456227,0.0002690892,0.0005249732],"genre_scores_gemma":[0.1903104,0.0005132964,0.8040035,0.0001400914,0.000134662,0.0003665399,0.001168277,0.0002804009,0.00308282],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01051103,"threshold_uncertainty_score":0.02089971,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01287646303858669,"score_gpt":0.2691161265900028,"score_spread":0.2562396635514161,"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."}}