{"id":"W2296973526","doi":"10.1145/2890104","title":"Enhanced Reweighted MRFs for Efficient Fashion Image Parsing","year":2016,"lang":"en","type":"article","venue":"ACM Transactions on Multimedia Computing Communications and Applications","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Markov random field; Parsing; Conditional random field; Artificial intelligence; Smoothing; Random forest; Pattern recognition (psychology); Markov chain; Image (mathematics); Set (abstract data type); Machine learning; Computer vision; Image segmentation","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":["sts"],"consensus_categories":[],"category_scores_codex":[0.0003140683,0.0002021219,0.000201742,0.0001544754,0.001385184,0.000141339,0.001480794,0.00007882289,0.00000779234],"category_scores_gemma":[0.00006974229,0.0001620119,0.0001110688,0.0004386526,0.0002391276,0.0002074469,0.0001114231,0.0001472908,0.00003166628],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006381299,"about_ca_system_score_gemma":0.00004876327,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000810254,"about_ca_topic_score_gemma":0.00001022351,"domain_scores_codex":[0.9985425,0.0001305628,0.0003742439,0.000507413,0.000139828,0.0003054594],"domain_scores_gemma":[0.9947584,0.002263803,0.0001557495,0.002428856,0.0002582857,0.0001349113],"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":[0.000005946502,0.000262565,0.000004240211,0.000007250271,0.00003467585,6.273967e-8,0.0003379312,0.0009478049,0.04364911,0.0043874,0.00004776146,0.9503152],"study_design_scores_gemma":[0.001394284,0.0001208619,0.0003464546,0.0001242433,0.00006158598,0.000005498681,0.000157844,0.9532024,0.02890327,0.002472094,0.01270038,0.0005110568],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001079386,0.00009407663,0.9904411,0.006920511,0.0001048325,0.0008859067,0.00003357237,0.0002414575,0.0001991506],"genre_scores_gemma":[0.55423,0.0001873231,0.4451052,0.0000877311,0.00004607481,0.000280486,0.000007980248,0.00001227299,0.00004294524],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9522547,"threshold_uncertainty_score":0.9999149,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02184744000109047,"score_gpt":0.278291196220301,"score_spread":0.2564437562192106,"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."}}