{"id":"W2067248598","doi":"10.1109/34.908970","title":"Encoding visual information using anisotropic transformations","year":2001,"lang":"en","type":"article","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","topic":"Medical Image Segmentation Techniques","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Anisotropy; Artificial intelligence; Computer science; Entropy (arrow of time); Anisotropic diffusion; Information theory; Scale space; Encoding (memory); Computer vision; Pattern recognition (psychology); Statistical physics; Mathematics; Image processing; Image (mathematics); Physics; Optics","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":[0.0001822776,0.0001549283,0.0001928135,0.0007205716,0.0002603136,0.0002251786,0.000278139,0.00005355391,0.00023094],"category_scores_gemma":[0.00000454844,0.0001417515,0.0001407342,0.001266694,0.0000491106,0.00147594,0.000003534748,0.0001878722,0.00002949293],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005124443,"about_ca_system_score_gemma":0.00002102453,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004917497,"about_ca_topic_score_gemma":0.0001548146,"domain_scores_codex":[0.9987595,0.00006259162,0.0004535224,0.0002182862,0.0003148551,0.0001912149],"domain_scores_gemma":[0.9993851,0.00006482202,0.0001046759,0.0002391722,0.00008047673,0.0001257744],"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":[0.000003372556,0.0000678033,0.0002787298,0.00001026235,0.0001186708,0.000003394743,0.000666142,0.006579863,0.0008008464,0.00005884164,0.000003249406,0.9914088],"study_design_scores_gemma":[0.00009293174,0.00009264682,0.000307089,0.00001929224,0.0001922908,0.00002154272,0.0001220202,0.7785471,0.2201969,0.0001421362,0.00006147425,0.0002046338],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003503652,0.00001820018,0.9957392,0.0002109853,0.0001008345,0.0001335762,0.00001042739,0.0001677778,0.0001153296],"genre_scores_gemma":[0.9791055,0.0004030717,0.01979281,0.000636988,0.000009836146,0.00001586484,0.000007217953,0.000004414268,0.00002434245],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9912042,"threshold_uncertainty_score":0.5780458,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02456228513439488,"score_gpt":0.3088109809833258,"score_spread":0.2842486958489309,"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."}}