{"id":"W4230401652","doi":"10.1109/cvprw.2009.5206812","title":"Increased discrimination in level set methods with embedded conditional random fields","year":2009,"lang":"en","type":"article","venue":"2009 IEEE Conference on Computer Vision and Pattern Recognition","topic":"Image and Object Detection Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia; University of Alberta","funders":"","keywords":"CRFS; Conditional random field; Discriminative model; Embedding; Computer science; Artificial intelligence; Segmentation; Set (abstract data type); Pattern recognition (psychology); Level set (data structures); Prior probability; Image segmentation; Random field; Image (mathematics); Energy (signal processing); Mathematics; Statistics","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":[0.0004491626,0.0002133783,0.00023138,0.0003405103,0.0001070722,0.0002880988,0.0002200969,0.0001213385,0.00004188959],"category_scores_gemma":[0.00001240409,0.0001747132,0.00004487409,0.000219798,0.00003378652,0.000473051,0.00002954482,0.0002360613,0.00001928686],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002817175,"about_ca_system_score_gemma":0.00004006026,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004319653,"about_ca_topic_score_gemma":0.00004326432,"domain_scores_codex":[0.9984699,0.0003335624,0.000275753,0.0004624665,0.0002551498,0.0002031499],"domain_scores_gemma":[0.9992639,0.0001378071,0.0001163338,0.0002251102,0.0001704422,0.00008636161],"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":[0.00008278404,0.0001027868,0.00002485074,0.00001003135,0.00000491848,0.00002406136,0.0002781731,0.00001047374,0.0007759244,0.0001172848,0.0006536437,0.9979151],"study_design_scores_gemma":[0.01066399,0.007933835,0.08476894,0.001375188,0.00003719777,0.000333575,0.0001087678,0.6534889,0.1774962,0.061896,0.000317593,0.001579843],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03787987,0.00001031733,0.9603487,0.0006853952,0.000164478,0.0002823671,0.00001973486,0.0001400524,0.0004690315],"genre_scores_gemma":[0.9203949,0.00003841906,0.0765956,0.002736066,0.00007852834,0.00002382509,0.00009751654,0.000006388934,0.00002876314],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9963352,"threshold_uncertainty_score":0.7124597,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06696593770985532,"score_gpt":0.3422361822012467,"score_spread":0.2752702444913914,"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."}}