{"id":"W4254782311","doi":"10.1109/icpr.2004.1334595","title":"Steerable kernels for arbitrarily-sampled spaces","year":2004,"lang":"en","type":"article","venue":"Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004.","topic":"Medical Image Segmentation Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Pixel; Image (mathematics); Computer science; Space (punctuation); Computer vision; Kernel (algebra); Artificial intelligence; Mathematics; Pure mathematics","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":[0.0004799265,0.0002792163,0.000279708,0.0002410732,0.0001603619,0.0003859566,0.00183598,0.0001217908,0.0003476631],"category_scores_gemma":[0.0003737405,0.0002265221,0.0001803634,0.000294013,0.0001533965,0.0009371914,0.0001740368,0.0002707321,0.00006733668],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001940268,"about_ca_system_score_gemma":0.0001813258,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009812468,"about_ca_topic_score_gemma":0.00001200381,"domain_scores_codex":[0.9975632,0.00001548128,0.0005935839,0.0005650356,0.0009076857,0.0003550178],"domain_scores_gemma":[0.9973732,0.00009416242,0.0005590277,0.0002308024,0.001610616,0.0001321653],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0005956461,0.00363698,0.009338176,0.00106707,0.001137073,0.00001391645,0.00580073,0.000196027,0.1125094,0.2469624,0.1040142,0.5147284],"study_design_scores_gemma":[0.002794375,0.0004368576,0.001371882,0.001056542,0.00004243544,0.00003581632,0.0002752239,0.002240405,0.7143859,0.2759021,0.000860908,0.0005975253],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03116196,0.0000513612,0.9324323,0.01317472,0.001351553,0.001480547,0.0002327031,0.0003943952,0.01972047],"genre_scores_gemma":[0.90635,0.00005835136,0.08704308,0.004144903,0.0003115257,0.0003889958,0.00005806107,0.00004155272,0.001603542],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8751881,"threshold_uncertainty_score":0.9237303,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06031484864399905,"score_gpt":0.3052575130212499,"score_spread":0.2449426643772508,"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."}}