{"id":"W2096781507","doi":"10.1109/icip.1998.999019","title":"Selective image diffusion: application to disparity estimation","year":2002,"lang":"en","type":"article","venue":"","topic":"Medical Image Segmentation Techniques","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Regularization (linguistics); Computer science; Inverse problem; Term (time); A priori and a posteriori; Bayesian probability; Eigenvalues and eigenvectors; Algorithm; Computation; Transformation (genetics); Context (archaeology); Diffusion; Image processing; Image (mathematics); Artificial intelligence; Anisotropic diffusion; Mathematical optimization; Applied mathematics; Mathematics; Mathematical analysis; Physics","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":[0.0001259022,0.00007321921,0.00007252731,0.00007271288,0.00007897137,0.00009926393,0.0003701199,0.00003129183,0.0002099026],"category_scores_gemma":[0.0001028358,0.0000646298,0.00001996814,0.000459642,0.00002137865,0.0005394287,0.000132811,0.00006798779,0.0006218552],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005713569,"about_ca_system_score_gemma":0.000005523007,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003648238,"about_ca_topic_score_gemma":0.00000472612,"domain_scores_codex":[0.9991462,0.00003423407,0.0001520153,0.0002760088,0.0002589113,0.0001326223],"domain_scores_gemma":[0.9993634,0.00004565416,0.00004116004,0.000337923,0.00008482386,0.0001271056],"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":[0.000001194071,0.0001581694,0.0001323587,0.00000953839,0.000003323685,0.000001443837,0.0006355975,0.00001339632,0.04330409,0.009227638,0.06096952,0.8855437],"study_design_scores_gemma":[0.0001359922,0.00006497746,0.004176806,0.000007248721,0.000002075045,0.000003909774,0.000008289934,0.8357739,0.1552652,0.003901867,0.0005061869,0.0001534974],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.000411066,0.000004609889,0.9873991,0.002493608,0.00004257904,0.0003494,4.667716e-7,0.0006042963,0.008694896],"genre_scores_gemma":[0.1758779,0.000003958729,0.8214872,0.001746624,0.00002053037,0.0001183377,0.000002538706,0.000003948331,0.0007389293],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8853902,"threshold_uncertainty_score":0.7992898,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01093091622261577,"score_gpt":0.2788137288571699,"score_spread":0.2678828126345541,"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."}}