{"id":"W2040555343","doi":"10.1145/2661229.2661275","title":"Hierarchical diffusion curves for accurate automatic image vectorization","year":2014,"lang":"en","type":"article","venue":"ACM Transactions on Graphics","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":45,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs","keywords":"Computer science; Vector graphics; Raster graphics; Artificial intelligence; Curve fitting; Computer vision; Vectorization (mathematics); Laplace operator; Smoothing; Representation (politics); Computer graphics; Pattern recognition (psychology); Mathematics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0002216123,0.0001386714,0.0001412162,0.0002049057,0.0003697388,0.00009311608,0.0006022081,0.00005017049,0.00002077419],"category_scores_gemma":[0.0002027186,0.000124838,0.0001160225,0.0005623626,0.00005700739,0.0006139401,0.0000138266,0.0001991474,0.00001804209],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001625536,"about_ca_system_score_gemma":0.0000231879,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002213682,"about_ca_topic_score_gemma":0.000003355937,"domain_scores_codex":[0.9989288,0.00007618369,0.0002190483,0.0003218029,0.0002325662,0.0002216078],"domain_scores_gemma":[0.9985524,0.0004882334,0.00006871824,0.0006945473,0.0001005815,0.00009550789],"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":[0.00001483763,0.0003005609,0.00002986392,0.0001668894,0.00002121515,0.000001050896,0.0002726563,0.0002572638,0.005843295,0.03122141,0.0004526396,0.9614183],"study_design_scores_gemma":[0.0006142268,0.0002012936,0.001060321,0.0001868363,0.00001773604,0.000006185903,0.000007194074,0.9330512,0.002609813,0.05593945,0.00606445,0.0002413381],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0007604737,0.00003219355,0.992871,0.005311215,0.0004236673,0.0002471543,0.000005805401,0.0002574191,0.00009100052],"genre_scores_gemma":[0.4736122,0.0004770961,0.5222763,0.003299554,0.00006050349,0.0001062634,0.00001612397,0.00003022405,0.0001216982],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.961177,"threshold_uncertainty_score":0.5090744,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01803372760930425,"score_gpt":0.2916603542031201,"score_spread":0.2736266265938159,"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."}}