{"id":"W2059155248","doi":"10.1109/icip.2006.312553","title":"Optical-Flow Based on an Edge-Avoidance Procedure","year":2006,"lang":"en","type":"article","venue":"","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Optical flow; Classification of discontinuities; Regularization (linguistics); Motion (physics); Artificial intelligence; Computer vision; Motion estimation; Motion field; Algorithm; Computer science; Enhanced Data Rates for GSM Evolution; Mathematics; Parametric statistics; Image (mathematics); Mathematical analysis","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":[0.00009138866,0.0001055243,0.00008380291,0.00005801635,0.00009701199,0.0001224653,0.0004486444,0.00002578693,0.0000398012],"category_scores_gemma":[0.00002836009,0.00008367994,0.00003041023,0.000242372,0.00002797964,0.0005305078,0.00004890752,0.0001000186,0.0001316323],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002152405,"about_ca_system_score_gemma":0.00004293496,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003964489,"about_ca_topic_score_gemma":0.000004506957,"domain_scores_codex":[0.9990489,0.00001710743,0.0001209606,0.0003653351,0.0002158124,0.0002319064],"domain_scores_gemma":[0.999323,0.00004024242,0.00002596825,0.0004748027,0.00005006106,0.00008594852],"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":[0.00001943472,0.0006783237,0.0008297914,0.00002395319,0.00000195613,0.00004134715,0.00006152734,0.03999344,0.006025759,0.2237195,0.01572039,0.7128845],"study_design_scores_gemma":[0.0002331099,0.00007708831,0.002209798,0.00001656188,5.688909e-7,0.0000029664,0.000004016659,0.9762174,0.01117272,0.003266184,0.006658096,0.0001414176],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0005690485,0.00001368604,0.9457669,0.00199702,0.0001108353,0.00007901747,3.678346e-7,0.0003230697,0.05114008],"genre_scores_gemma":[0.3816152,4.712457e-7,0.6133693,0.003472602,0.0000718977,0.000006059809,0.000001765261,0.000007310935,0.001455332],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.936224,"threshold_uncertainty_score":0.3412369,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008516144646752906,"score_gpt":0.2572740783604328,"score_spread":0.2487579337136799,"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."}}