{"id":"W4220770939","doi":"10.1061/9780784483961.027","title":"Synthetic Training Image Dataset for Vision-Based 3D Pose Estimation of Construction Workers","year":2022,"lang":"en","type":"article","venue":"Construction Research Congress 2022","topic":"Occupational Health and Safety Research","field":"Health Professions","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Hudbay Minerals (Canada); University of Toronto","funders":"","keywords":"Pose; Artificial intelligence; Computer science; Economic shortage; 3D pose estimation; Training (meteorology); Estimation; Computer vision; Image (mathematics); Artificial neural network; Scalability; Machine learning; Training set; Pattern recognition (psychology); Engineering","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","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.008141434,0.0001942678,0.0004195249,0.001077907,0.004585091,0.00003349807,0.0004744516,0.0001569428,0.007794282],"category_scores_gemma":[0.003690539,0.0002083732,0.0001102261,0.001351548,0.001210396,0.000339442,0.0003560913,0.001821005,0.00006197127],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007642009,"about_ca_system_score_gemma":0.005325646,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002909963,"about_ca_topic_score_gemma":0.00003159835,"domain_scores_codex":[0.9920059,0.00332424,0.001047257,0.0006443388,0.001911101,0.001067136],"domain_scores_gemma":[0.9899243,0.007216594,0.0004500481,0.0006719219,0.001381178,0.0003559508],"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":[0.01303567,0.0005458232,0.03255199,0.004430143,0.0002012734,0.0000363352,0.001743678,0.01063817,0.002832267,0.01868114,0.1637098,0.7515938],"study_design_scores_gemma":[0.01712576,0.003890202,0.01854189,0.001406475,0.0001278537,0.0001418147,0.08107722,0.522582,0.0009868611,0.01240186,0.3403978,0.00132024],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6829908,0.0014447,0.07199547,0.03159833,0.03303246,0.04238812,0.1166248,0.0007645564,0.01916067],"genre_scores_gemma":[0.9279763,0.00006682403,0.04875998,0.0002965217,0.0005164797,0.008515298,0.01290783,0.0001124602,0.0008483449],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7502735,"threshold_uncertainty_score":0.9967108,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1339045910671556,"score_gpt":0.5216168335968322,"score_spread":0.3877122425296766,"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."}}