{"id":"W2110593503","doi":"10.1109/iccv.2009.5459263","title":"Globally optimal segmentation of multi-region objects","year":2009,"lang":"en","type":"article","venue":"","topic":"Medical Image Segmentation Techniques","field":"Computer Science","cited_by":128,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Segmentation; Computer science; Artificial intelligence; Image segmentation; Boundary (topology); Object (grammar); ENCODE; Computer vision; Domain (mathematical analysis); Scale-space segmentation; Pattern recognition (psychology); Graph; Topology (electrical circuits); Mathematics; Theoretical computer science; Combinatorics","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":[0.0001311839,0.00007159871,0.00009012812,0.00006626694,0.00002457205,0.00004299468,0.0004238041,0.00003471794,0.00002587627],"category_scores_gemma":[0.00003551776,0.0000622951,0.00003438129,0.0002306274,0.0000281433,0.0004847456,0.00005062625,0.00004182115,0.00001425388],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002999582,"about_ca_system_score_gemma":0.00003318736,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001690777,"about_ca_topic_score_gemma":0.000001509629,"domain_scores_codex":[0.9991554,0.00003681971,0.0002104738,0.0001814009,0.0002945875,0.0001213066],"domain_scores_gemma":[0.9995114,0.00002029434,0.00008828792,0.0002307936,0.00008189027,0.00006731267],"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":[0.00000817865,0.0003198963,0.0001798217,0.00001133072,0.0000100612,0.0000224086,0.0009269773,0.00007457889,0.1284524,0.01593939,0.005766195,0.8482887],"study_design_scores_gemma":[0.0005959887,0.0003337879,0.003572886,0.0000222259,0.000004009519,0.00001625644,0.00008306815,0.03311117,0.9610022,0.001099744,0.0000203781,0.0001383213],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001348835,0.00002270988,0.9942867,0.0003638861,0.00004716665,0.0001604805,2.384915e-7,0.0002807388,0.00348929],"genre_scores_gemma":[0.2698518,0.00001021876,0.728725,0.001192354,0.000008991085,0.000002978942,0.000001809479,0.0000015823,0.0002053495],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8481504,"threshold_uncertainty_score":0.254032,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02252566524404762,"score_gpt":0.3053756206244485,"score_spread":0.2828499553804009,"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."}}