{"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":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.001437038,0.0001218315,0.0001132048,0.00006848454,0.002774948,0.0004155562,0.0008449449,0.00001806549,0.0004882331],"category_scores_gemma":[0.00020618,0.00007621237,0.00006832762,0.0002680476,0.00001733663,0.0004193365,0.0005427258,0.0002014617,0.00004186813],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006368212,"about_ca_system_score_gemma":0.00002891111,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002513384,"about_ca_topic_score_gemma":0.00007305086,"domain_scores_codex":[0.9986212,0.000227964,0.0002739196,0.0003474663,0.0002908601,0.0002385423],"domain_scores_gemma":[0.9981191,0.0009857677,0.000173875,0.0006068433,0.00006271058,0.00005170813],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000009294393,0.0000624705,0.000002893005,0.000006589647,0.00002265546,0.000001087605,0.001029998,0.001402235,0.003216806,0.004845534,0.804755,0.1846454],"study_design_scores_gemma":[0.0005922119,0.0003546736,0.0001703822,0.00001102979,0.00004598789,0.00008449036,0.001797534,0.3875709,0.02122356,0.008776939,0.579017,0.0003553226],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003176173,0.00002471467,0.9888057,0.005743526,0.0003435214,0.0009390872,0.0005236469,0.00013719,0.0003064962],"genre_scores_gemma":[0.8687696,0.000003275288,0.0895765,0.03074389,0.0005057459,0.002444617,0.004558641,0.00005815499,0.0033396],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8992292,"threshold_uncertainty_score":0.9985233,"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."}}