{"id":"W2436179633","doi":"10.1109/cvpr.2016.267","title":"Hedgehog Shape Priors for Multi-Object Segmentation","year":2016,"lang":"en","type":"article","venue":"","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":28,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"National Institutes of Health; Natural Sciences and Engineering Research Council of Canada; McGill University","keywords":"Convexity; Segmentation; Computer science; Star (game theory); Cut; Medial axis; Constraint (computer-aided design); Mathematics; Artificial intelligence; Computer vision; Image segmentation; Geometry; Mathematical analysis","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":[0.00006035938,0.00007385186,0.00006126761,0.00003234224,0.00009396097,0.00002747971,0.0003626285,0.00002246482,0.00002219509],"category_scores_gemma":[0.00002219769,0.00004742071,0.00003685227,0.0001615487,0.000020758,0.0004093346,0.00008032365,0.00001856894,0.0001066024],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003517625,"about_ca_system_score_gemma":0.00001606553,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":9.219515e-7,"about_ca_topic_score_gemma":0.00000612757,"domain_scores_codex":[0.9993266,0.00001097233,0.0001249988,0.000282339,0.00007931249,0.0001757922],"domain_scores_gemma":[0.999388,0.0001524799,0.00005000975,0.0003070553,0.0000504381,0.00005202919],"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":[0.000004992839,0.00004829727,0.0003069587,0.000004926634,0.000006728265,3.803221e-7,0.0001113831,0.00005902568,0.07971666,0.08865523,0.002383698,0.8287017],"study_design_scores_gemma":[0.003834021,0.0002807506,0.008847586,0.00004262989,0.00001360645,0.00001670393,0.00004849146,0.6347654,0.2790842,0.02294838,0.04928973,0.0008285072],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004076472,0.00001507401,0.9930478,0.001782105,0.0001032915,0.0004577332,0.000002173597,0.0002578348,0.0002574792],"genre_scores_gemma":[0.1599069,0.00001532298,0.8366172,0.000545618,0.00005761725,0.0002412579,0.000001638116,0.000008903243,0.00260548],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8278732,"threshold_uncertainty_score":0.193376,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04845171371433264,"score_gpt":0.3231487296809034,"score_spread":0.2746970159665707,"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."}}