{"id":"W3202224009","doi":"10.1109/iccv48922.2021.01081","title":"EventHPE: Event-based 3D Human Pose and Shape Estimation","year":2021,"lang":"en","type":"article","venue":"2021 IEEE/CVF International Conference on Computer Vision (ICCV)","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Guelph; University of Alberta","funders":"","keywords":"Computer science; Optical flow; Artificial intelligence; Event (particle physics); Coherence (philosophical gambling strategy); Computer vision; Flow (mathematics); Pose; Pattern recognition (psychology); Image (mathematics); 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","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000266973,0.0002867794,0.0002513621,0.000304806,0.0002913798,0.0009141432,0.0006115133,0.0001231948,0.002520922],"category_scores_gemma":[0.0000278295,0.0002945147,0.0001282656,0.0002647692,0.00004869288,0.0008063189,0.0002414292,0.0003016548,0.0004673715],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001211284,"about_ca_system_score_gemma":0.0001785278,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001298913,"about_ca_topic_score_gemma":0.00001782141,"domain_scores_codex":[0.9974844,0.0001854811,0.0004962102,0.0008284764,0.0007387036,0.0002666839],"domain_scores_gemma":[0.998336,0.0001225154,0.0002275079,0.0004542849,0.0006877102,0.0001720418],"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":[0.000057333,0.001064698,0.0001565589,0.0000523251,0.0001333311,0.0003428684,0.00034191,0.003927861,0.0220275,0.09010127,0.01407842,0.867716],"study_design_scores_gemma":[0.0009186915,0.0002993459,0.001893275,0.0003726873,0.00001109196,0.00005328474,0.00001441935,0.9810686,0.007942527,0.004316785,0.002756961,0.0003523418],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09864441,0.00004028064,0.8857291,0.006577563,0.003478797,0.0002456101,0.00003613221,0.0002012729,0.005046879],"genre_scores_gemma":[0.9701576,0.00004335698,0.02599704,0.001983709,0.0004956066,0.0000248009,0.0002398264,0.00001846192,0.001039588],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9771407,"threshold_uncertainty_score":0.9999507,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03629010757355457,"score_gpt":0.3264730224435097,"score_spread":0.2901829148699551,"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."}}