{"id":"W2532567985","doi":"10.1109/iccv.2009.5459253","title":"Optical flow estimation on coarse-to-fine region-trees using discrete optimization","year":2009,"lang":"en","type":"article","venue":"","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":64,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Optical flow; Computer science; Discretization; Tree (set theory); Benchmark (surveying); Global optimization; Image segmentation; Algorithm; Continuous optimization; Sampling (signal processing); Discrete optimization; Displacement (psychology); Segmentation; Optimization problem; Artificial intelligence; Mathematical optimization; Mathematics; Image (mathematics); Computer vision; Multi-swarm optimization; Geology","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":[0.00008597218,0.0001111422,0.0001041691,0.0001212692,0.0001213648,0.0001521249,0.0002315247,0.00002708398,0.00001355706],"category_scores_gemma":[0.0001446034,0.00009310126,0.00003143867,0.0003452554,0.00001409287,0.0006666203,0.0000465858,0.00006910106,0.00003340796],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004481038,"about_ca_system_score_gemma":0.00002082647,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001351139,"about_ca_topic_score_gemma":6.291814e-7,"domain_scores_codex":[0.9991066,0.00002514351,0.0001666489,0.0002986265,0.000213033,0.0001899617],"domain_scores_gemma":[0.9994111,0.00004256887,0.0000391933,0.000337141,0.00005575236,0.0001142318],"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":[0.000003919151,0.0000169611,0.000002879822,5.222125e-7,6.915984e-7,0.000004033142,0.00003549532,0.7173254,0.0001798983,0.03675133,0.00007272511,0.2456061],"study_design_scores_gemma":[0.0001743207,0.0001059343,0.00008324823,0.0000414506,0.000002014856,0.00001495704,0.000006968646,0.9940226,0.002240712,0.003038367,0.000138192,0.0001312068],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0002317547,0.000007493014,0.9935745,0.002789023,0.0001169806,0.0001161349,1.665671e-7,0.0002112349,0.002952719],"genre_scores_gemma":[0.1865672,0.000001968267,0.8123186,0.0009892692,0.00002295422,9.666704e-7,0.00000195673,0.000004754661,0.00009238227],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2766972,"threshold_uncertainty_score":0.3796559,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02512268699819252,"score_gpt":0.3084698356927759,"score_spread":0.2833471486945833,"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."}}