{"id":"W1582205079","doi":"10.1109/crv.2015.50","title":"Improving Segmentation Boundaries with Nonparametric Image Parsing","year":2015,"lang":"en","type":"article","venue":"","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Artificial intelligence; Computer science; Pixel; Conditional random field; Parsing; Segmentation; Image segmentation; Pattern recognition (psychology); Computer vision; Nonparametric statistics; Segmentation-based object categorization; Scale-space segmentation; Mathematics; Statistics","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":[0.0002097535,0.0001003759,0.00009792645,0.0001315521,0.0001344655,0.0007840291,0.0002781483,0.00002433818,0.000002586444],"category_scores_gemma":[0.000118476,0.00007498427,0.00001802005,0.0007417963,0.00007215178,0.002289642,0.0001172775,0.00007713056,0.0000296683],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007866888,"about_ca_system_score_gemma":0.0001487989,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008289309,"about_ca_topic_score_gemma":0.000005548894,"domain_scores_codex":[0.9991536,0.00002297174,0.0001254946,0.000243849,0.0002572338,0.0001968748],"domain_scores_gemma":[0.9993432,0.00004500032,0.00007339669,0.0002810251,0.0001816343,0.00007576575],"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":[0.0001000844,0.0001613508,0.002449652,0.00005152397,0.00003122302,0.0001216624,0.001938222,0.00002393885,0.05897676,0.04021306,0.008175991,0.8877565],"study_design_scores_gemma":[0.0003729257,0.0004307922,0.00007828933,0.00001407203,0.000006095234,0.00004449459,0.0001427348,0.007739924,0.9761221,0.009127895,0.005671182,0.0002494995],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005345554,0.0001249232,0.9890471,0.0001937308,0.00007240356,0.0001435824,4.206827e-7,0.0005146328,0.004557728],"genre_scores_gemma":[0.1765065,0.000003906444,0.823025,0.0002774264,0.00002074683,0.00000777022,0.000001655838,0.000007119471,0.000149878],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9171453,"threshold_uncertainty_score":0.756041,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02191416384212106,"score_gpt":0.2863495210653719,"score_spread":0.2644353572232508,"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."}}