{"id":"W2164383578","doi":"10.1109/cvpr.2009.5206561","title":"Fast normalized cut with linear constraints","year":2009,"lang":"en","type":"article","venue":"2009 IEEE Conference on Computer Vision and Pattern Recognition","topic":"Sparse and Compressive Sensing Techniques","field":"Engineering","cited_by":79,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Mathematical optimization; Computation; Variety (cybernetics); Image segmentation; Segmentation; Linear programming; Algorithm; Image (mathematics); Maximum cut; Artificial intelligence; Mathematics; Theoretical computer science","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":[0.00004651135,0.0002071193,0.0001914667,0.0001054822,0.00005756979,0.00009266398,0.00007385301,0.00008718188,0.00009433184],"category_scores_gemma":[9.810492e-7,0.0001702559,0.00003079581,0.00006644416,0.00004847774,0.0001177567,0.000007770559,0.0001800741,0.00007445546],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001018998,"about_ca_system_score_gemma":0.000008240388,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003903523,"about_ca_topic_score_gemma":0.000005066908,"domain_scores_codex":[0.9992554,0.0000325609,0.0001651771,0.0002255634,0.0001346405,0.0001866543],"domain_scores_gemma":[0.9996108,0.00002370965,0.00003870383,0.0001439565,0.00009444256,0.00008838875],"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":[0.00002829045,0.00003877744,0.00003615271,0.000008135838,0.00001190956,0.00003762378,0.00006634996,0.0001959332,0.002574326,0.000015999,0.001487039,0.9954995],"study_design_scores_gemma":[0.002382299,0.002787139,0.007083198,0.002198769,0.00004475554,0.0002593652,0.00003333664,0.9255282,0.0562696,0.001389033,0.0009443463,0.001079916],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4404705,0.00002189014,0.5545692,0.0001371592,0.0002622704,0.0002007749,0.0000255642,0.0005893329,0.003723228],"genre_scores_gemma":[0.9938436,0.0001319197,0.005061967,0.0007516625,0.0001337279,0.000003292248,0.00004432631,0.00001439185,0.00001513147],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9944196,"threshold_uncertainty_score":0.6942834,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03094089659702663,"score_gpt":0.2537180239615252,"score_spread":0.2227771273644985,"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."}}