{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001106266,0.003391084,0.001621258,0.001525796,0.000499979,0.0009943916,0.002842865,0.001690033,0.004120496],"category_scores_gemma":[0.003406096,0.0009582771,0.001557853,0.00105969,0.001298627,0.001935882,0.002081685,0.00235778,0.004998258],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000629359,"about_ca_system_score_gemma":0.001323035,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008051557,"about_ca_topic_score_gemma":0.01671406,"domain_scores_codex":[0.9989973,0.0001978129,0.00002665978,0.0004946623,0.0001919876,0.00009160041],"domain_scores_gemma":[0.9989694,0.0002747626,0.00009584299,0.0003790295,0.0001893696,0.00009157114],"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":[0.0004389529,0.0004865511,0.004178861,0.0002495177,0.0002725721,0.0001544256,0.0001994676,0.1824953,0.01557753,0.004776414,0.02936143,0.7618089],"study_design_scores_gemma":[0.00003992825,0.0001315911,0.001944886,0.00003870473,0.00002744441,0.00029936,0.00005080804,0.9709477,0.00940752,0.009479009,0.007589979,0.0000430622],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0128095,0.0004343675,0.9700124,0.0001422144,0.0001753514,0.0001867431,0.0009550037,0.01380564,0.001478685],"genre_scores_gemma":[0.2479307,0.0009582083,0.7210326,0.0005877999,0.0004078182,0.0005795784,0.01380673,0.001794184,0.01290236],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008051557,"threshold_uncertainty_score":0.01600933,"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."}}