{"id":"W4383224354","doi":"10.1049/cvi2.12222","title":"Enhancing human parsing with region‐level learning","year":2023,"lang":"en","type":"article","venue":"IET Computer Vision","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Innovation and Technology Fund","keywords":"Parsing; Computer science; Artificial intelligence; Bottom-up parsing; Benchmark (surveying); Top-down parsing; Machine learning; Natural language processing; Key (lock); Code (set theory); Programming language; Set (abstract data type)","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":[0.0002348165,0.0001395125,0.0001392638,0.0002489104,0.0005343027,0.0003317703,0.0003072726,0.00005377369,0.00001034429],"category_scores_gemma":[0.000004523836,0.0001221743,0.0000527529,0.0005802123,0.00002397653,0.0006725516,0.0002049516,0.0002188416,0.000410956],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000315834,"about_ca_system_score_gemma":0.00002611446,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008010286,"about_ca_topic_score_gemma":0.000006897018,"domain_scores_codex":[0.9987251,0.00008624784,0.0002003241,0.0004199649,0.0002772773,0.0002911527],"domain_scores_gemma":[0.9993867,0.00007323702,0.00009885898,0.000278041,0.00008213195,0.00008101948],"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":[0.00003673684,0.0002318278,0.001450329,0.0001411495,0.00008681474,0.0009947064,0.006878954,0.009695868,0.03118619,0.005561798,0.03585413,0.9078815],"study_design_scores_gemma":[0.00279534,0.003070129,0.068288,0.002080217,0.00003283117,0.0006229734,0.0002204871,0.8260255,0.03306855,0.008416845,0.05357531,0.001803757],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2425536,0.000005220792,0.7554651,0.000324608,0.0002867632,0.0000802913,1.935739e-7,0.0007613173,0.000522864],"genre_scores_gemma":[0.9772077,0.000007281154,0.02138194,0.0002760719,0.0003148206,0.000005183026,0.00001712623,0.00001709996,0.0007727704],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9060777,"threshold_uncertainty_score":0.5282146,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04161570399251161,"score_gpt":0.2856353899765273,"score_spread":0.2440196859840157,"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."}}