{"id":"W4293868182","doi":"10.1109/crv55824.2022.00009","title":"A Simple Method to Boost Human Pose Estimation Accuracy by Correcting the Joint Regressor for the Human3.6m Dataset","year":2022,"lang":"en","type":"article","venue":"","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Ground truth; Computer science; Joint (building); Artificial intelligence; Estimation; Set (abstract data type); Pose; Computer vision; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002758849,0.005967282,0.001633679,0.002027092,0.0008265309,0.001402515,0.002619676,0.001937304,0.01790351],"category_scores_gemma":[0.007913466,0.0009596628,0.002107814,0.001454935,0.0007558686,0.001529488,0.002562386,0.002451994,0.02495828],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008288859,"about_ca_system_score_gemma":0.00125414,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01469263,"about_ca_topic_score_gemma":0.05212627,"domain_scores_codex":[0.9964113,0.0005814334,0.0001729454,0.001597769,0.0009425179,0.0002941233],"domain_scores_gemma":[0.9977628,0.0003556708,0.0001411385,0.001073581,0.0005699625,0.0000967967],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0008216077,0.0005046297,0.01182298,0.001221748,0.0007791692,0.0002256917,0.0001523725,0.03357555,0.03621231,0.001722304,0.3015004,0.6114613],"study_design_scores_gemma":[0.0005190641,0.001155614,0.04901582,0.0005617637,0.0005320006,0.002583542,0.0003843506,0.5066875,0.1314403,0.009344094,0.2973929,0.0003831657],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06484148,0.005143583,0.5987253,0.0009530586,0.0034025,0.001205423,0.109258,0.1944348,0.02203595],"genre_scores_gemma":[0.1939819,0.001038226,0.5160083,0.00133602,0.0004160326,0.001270374,0.2585459,0.006559398,0.02084379],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01790351,"threshold_uncertainty_score":0.05989319,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06499098198111528,"score_gpt":0.3704570765127758,"score_spread":0.3054660945316605,"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."}}