{"id":"W4324107430","doi":"10.48550/arxiv.2303.05691","title":"Human Pose Estimation from Ambiguous Pressure Recordings with Spatio-temporal Masked Transformers","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Transformer; Estimator; Pose; Encoder; Artificial intelligence; Architecture; Machine learning; Estimation; Computer vision; Engineering","routes":{"ca_aff":true,"ca_fund":true,"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"],"consensus_categories":[],"category_scores_codex":[0.0001522429,0.0003416454,0.000328335,0.000354442,0.0003106848,0.0002531011,0.0008103544,0.0002918689,0.000138585],"category_scores_gemma":[0.000008102275,0.0003776298,0.0001669454,0.0004634022,0.00007918951,0.0008473567,0.000285717,0.0005540973,0.0002137599],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001195041,"about_ca_system_score_gemma":0.0001260672,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003315344,"about_ca_topic_score_gemma":0.0008257913,"domain_scores_codex":[0.9980913,0.0001035395,0.0002462881,0.00109285,0.0001594071,0.0003066309],"domain_scores_gemma":[0.9987156,0.00003410388,0.0003256134,0.0006169209,0.0001553602,0.0001523926],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0007097136,0.001083176,0.01715389,0.001149833,0.002894104,0.002877439,0.00707046,0.8642235,0.0005942658,0.03651788,0.01026316,0.05546251],"study_design_scores_gemma":[0.00185233,0.0003056063,0.01507701,0.0005487563,0.0004724098,0.000006777362,0.0002379657,0.8913627,0.0007297612,0.08692781,0.001186922,0.001292003],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5198105,0.000007116316,0.4775911,0.0001313506,0.0004701575,0.0003655272,0.00006254213,0.0006445795,0.00091711],"genre_scores_gemma":[0.9932741,0.00002620763,0.002521177,0.00006422046,0.0001068266,0.000003930344,0.0005022713,0.00003492496,0.003466354],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4750699,"threshold_uncertainty_score":0.9998676,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0703600781550504,"score_gpt":0.1979374823444734,"score_spread":0.127577404189423,"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."}}