{"id":"W2097333614","doi":"10.1109/crv.2007.32","title":"Figure-ground segmentation using a hierarchical conditional random field","year":2007,"lang":"en","type":"article","venue":"","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":49,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Conditional random field; Artificial intelligence; Segmentation; Computer science; Pattern recognition (psychology); Classifier (UML); Pixel; Image segmentation; Pascal (unit); Computer vision; Belief propagation; Random walker algorithm; Random forest; Image texture; Quadtree; Algorithm","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":[0.0002917279,0.00007645144,0.00008628356,0.00008222563,0.0001032956,0.00008277976,0.0002115185,0.00004692456,0.000119493],"category_scores_gemma":[0.00006533238,0.00006614621,0.00004647035,0.0002108938,0.00002732287,0.000734022,0.00006942899,0.0001248809,0.00001601189],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000378486,"about_ca_system_score_gemma":0.00003012037,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001878209,"about_ca_topic_score_gemma":0.000002438156,"domain_scores_codex":[0.9992206,0.00002154671,0.00017567,0.0001899808,0.0002097643,0.0001824946],"domain_scores_gemma":[0.9993719,0.000310911,0.00004247918,0.0001576892,0.00005460807,0.00006241397],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000318559,0.0002258563,0.001314791,0.00002898869,0.00004949249,0.000192742,0.0005350299,0.0000695346,0.1626787,0.4205965,0.005956125,0.4080338],"study_design_scores_gemma":[0.001718581,0.0002641955,0.001882593,0.00002337683,0.000008132504,0.00008598246,0.00004328359,0.0184681,0.7975851,0.1733079,0.006267122,0.0003456472],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.007692014,0.00003357386,0.9870178,0.0003484243,0.00007679987,0.0001307706,6.360858e-7,0.0002030453,0.004496931],"genre_scores_gemma":[0.4562266,0.000006662016,0.5413673,0.001903035,0.00008525354,0.000002965328,0.00000619402,0.000003991637,0.00039799],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6349064,"threshold_uncertainty_score":0.2697364,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02570679522102545,"score_gpt":0.3379340791307107,"score_spread":0.3122272839096853,"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."}}