{"id":"W4226239637","doi":"10.1109/cvpr52688.2022.00652","title":"ElePose: Unsupervised 3D Human Pose Estimation by Predicting Camera Elevation and Learning Normalizing Flows on 2D Poses","year":2022,"lang":"en","type":"preprint","venue":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Pose; Artificial intelligence; Computer science; Benchmark (surveying); Subspace topology; Prior probability; Machine learning; Unsupervised learning; Set (abstract data type); Pattern recognition (psychology); Computer vision","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":["metaepi_narrow","sts","scholarly_communication","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0009023153,0.0008063148,0.0007197891,0.0007804579,0.001592825,0.00183837,0.0005934636,0.0003961548,0.0009476925],"category_scores_gemma":[0.00004402042,0.0008616206,0.0001706877,0.0003126501,0.00007292483,0.000970197,0.0008388445,0.002344751,0.0000997232],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001591586,"about_ca_system_score_gemma":0.00009542178,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001811183,"about_ca_topic_score_gemma":0.00002704174,"domain_scores_codex":[0.9945927,0.001053739,0.001014071,0.001787442,0.000998645,0.0005533849],"domain_scores_gemma":[0.9975675,0.0003616501,0.0008327263,0.000586023,0.0003569228,0.0002951798],"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":[0.00006938943,0.0003671553,0.0006146435,0.000349572,0.0001000458,0.00004543599,0.001825861,0.002137784,0.003323871,0.00009370124,0.002444864,0.9886277],"study_design_scores_gemma":[0.001573864,0.00190537,0.002600373,0.001392125,0.00007727108,0.00006565903,0.000192664,0.987101,0.001233125,0.001566974,0.001073825,0.001217813],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7129101,0.00008431421,0.2820706,0.0006744133,0.001649026,0.0009254402,0.0001873263,0.0005880388,0.0009107804],"genre_scores_gemma":[0.9873207,0.0006130297,0.004875467,0.002439887,0.0005357662,0.0002285628,0.003696423,0.00008045896,0.0002097732],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9874099,"threshold_uncertainty_score":0.9999655,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03874067111674234,"score_gpt":0.2885738073207751,"score_spread":0.2498331362040328,"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."}}