{"id":"W2095844239","doi":"10.1109/cvpr.2004.1315232","title":"Multiscale conditional random fields for image labeling","year":2004,"lang":"en","type":"article","venue":"","topic":"Image Retrieval and Classification Techniques","field":"Computer Science","cited_by":843,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Canadian Institutes of Health Research","keywords":"Conditional random field; Markov random field; Computer science; Artificial intelligence; Pattern recognition (psychology); Probabilistic logic; Focus (optics); ENCODE; Pixel; Classifier (UML); Random field; Markov chain; Contextual image classification; CRFS; Computer vision; Image (mathematics); Machine learning; Mathematics; Image segmentation","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":[0.0001289435,0.00005534324,0.00006951296,0.0000316131,0.00009453813,0.00008142245,0.00025814,0.00003911126,0.0000335549],"category_scores_gemma":[0.00004799761,0.00004546376,0.00005620635,0.00009222302,0.00002763217,0.0003003544,0.0000370004,0.0000443186,0.00003677745],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001867809,"about_ca_system_score_gemma":0.00003615765,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008791333,"about_ca_topic_score_gemma":0.000001744277,"domain_scores_codex":[0.9994971,0.000007284029,0.0001203803,0.0001592684,0.0001011397,0.0001148747],"domain_scores_gemma":[0.9995934,0.0000751266,0.00002975313,0.0001592375,0.0001073183,0.00003517106],"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":[0.00002416713,0.0001385218,0.00001324141,0.00002442737,0.00001477729,0.000004881694,0.0001987776,0.00002740305,0.05294994,0.9171619,0.003761986,0.02567994],"study_design_scores_gemma":[0.002634968,0.00007552134,0.0001278409,0.00001100171,0.000003825277,0.0000132631,0.00001436157,0.01656135,0.7550148,0.2185578,0.006809196,0.0001760515],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0002142698,0.0000230167,0.9932181,0.003779436,0.00006651818,0.0001886939,0.000004807784,0.0002939559,0.002211228],"genre_scores_gemma":[0.3261137,0.000007865477,0.671787,0.0007993154,0.00004746702,0.00005974068,0.00001112462,0.000003728561,0.001170061],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7020649,"threshold_uncertainty_score":0.1853958,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01611067808887155,"score_gpt":0.2778233531800726,"score_spread":0.2617126750912011,"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."}}