{"id":"W2074551195","doi":"10.1109/tpami.2013.29","title":"Modeling Natural Images Using Gated MRFs","year":2013,"lang":"en","type":"article","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","topic":"Image Retrieval and Classification Techniques","field":"Computer Science","cited_by":62,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; University of New Brunswick","funders":"","keywords":"Latent variable; Artificial intelligence; Covariance; Pattern recognition (psychology); Covariance matrix; Markov random field; Pixel; Computer science; Markov chain; Gaussian; Mathematics; Algorithm; Image (mathematics); Image segmentation; Statistics; Machine learning","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":[0.00013478,0.0001843962,0.0002263192,0.0004271775,0.0002152364,0.0002828449,0.0003950454,0.00005196154,0.0001354637],"category_scores_gemma":[0.000003268079,0.0001505073,0.0001864146,0.001054424,0.00004928865,0.0005322694,0.000006299528,0.000244616,0.00003805304],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003345513,"about_ca_system_score_gemma":0.00001480981,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002642662,"about_ca_topic_score_gemma":0.00007553638,"domain_scores_codex":[0.99875,0.00006052855,0.0003252215,0.0004277861,0.0002250735,0.0002113943],"domain_scores_gemma":[0.9992266,0.00004357284,0.00006671794,0.0004019839,0.0001677689,0.00009336687],"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":[0.000002806903,0.00008869349,0.00007480952,0.00001087367,0.000227337,0.000002857912,0.000136082,0.01760064,0.01290672,0.00005948351,0.000003645771,0.9688861],"study_design_scores_gemma":[0.00002023707,0.00001804831,0.00005826756,0.000008619892,0.00008215231,0.000005534312,0.00001536701,0.6906655,0.3087529,0.000239908,0.000003489184,0.0001300233],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005371932,0.0001379178,0.9936931,0.0003506494,0.00009809525,0.0001262571,0.000006872699,0.0001859649,0.00002917826],"genre_scores_gemma":[0.9868272,0.0002125187,0.01247402,0.0002708765,0.00001046214,0.00001227142,0.000002290307,0.000008361927,0.0001820107],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9814553,"threshold_uncertainty_score":0.6137508,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02698940591231279,"score_gpt":0.281055005623605,"score_spread":0.2540655997112922,"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."}}