{"id":"W3184641178","doi":"10.1109/iccv48922.2021.01101","title":"Probabilistic Monocular 3D Human Pose Estimation with Normalizing Flows","year":2021,"lang":"en","type":"preprint","venue":"2021 IEEE/CVF International Conference on Computer Vision (ICCV)","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Bundesministerium für Bildung und Forschung; Ministry of Education; Deutsche Forschungsgemeinschaft","keywords":"Monocular; Benchmark (surveying); Generalization; Computer science; Probabilistic logic; Exploit; Artificial intelligence; Pose; Set (abstract data type); Posterior probability; Contrast (vision); Machine learning; Computer vision; Pattern recognition (psychology); Bayesian probability; Mathematics","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","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0004433093,0.0007286179,0.0006424543,0.0006300276,0.0003783585,0.002987415,0.001954661,0.000375757,0.001131194],"category_scores_gemma":[0.0000322902,0.0006918095,0.0002930768,0.0003172701,0.0000723745,0.001126502,0.001239382,0.001182719,0.0003301725],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004370919,"about_ca_system_score_gemma":0.0004611911,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001245832,"about_ca_topic_score_gemma":0.00009914042,"domain_scores_codex":[0.9950168,0.0003135116,0.0009398081,0.001790548,0.001473196,0.0004661],"domain_scores_gemma":[0.9961277,0.0001194922,0.0006800048,0.001247389,0.001581058,0.0002443159],"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":[0.0002185937,0.002648046,0.0001145599,0.0006591287,0.001177444,0.00160492,0.002937298,0.2255935,0.006081705,0.05676631,0.008399183,0.6937993],"study_design_scores_gemma":[0.0007089608,0.0004341561,0.0004243349,0.002025522,0.00004332553,0.00008874638,0.00002782624,0.9882304,0.001302182,0.005110537,0.0007844435,0.0008195805],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08692768,0.00003578268,0.8995736,0.001672078,0.005341105,0.0007485707,0.00004196132,0.0003318542,0.005327367],"genre_scores_gemma":[0.8086562,0.00007802391,0.1871275,0.0008294184,0.001313967,0.0001811206,0.001128444,0.00006288072,0.0006225294],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7626369,"threshold_uncertainty_score":0.9997819,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04328864255393678,"score_gpt":0.3100232181090402,"score_spread":0.2667345755551034,"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."}}