{"id":"W4386796790","doi":"10.23977/jeis.2023.080309","title":"MoCapDT: Temporal Guided Motion Capture Solving with Diffusion Transfer","year":2023,"lang":"en","type":"article","venue":"Journal of Electronics and Information Science","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Margin (machine learning); Artificial intelligence; Transfer of learning; Noise reduction; Data set; Exploit; Set (abstract data type); Diffusion; Encoder; Space (punctuation); Pattern recognition (psychology); Noise (video); Machine learning; Image (mathematics)","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009369412,0.00006777774,0.00008914458,0.0005113849,0.0002916488,0.0003885248,0.0002716494,0.00002876415,0.000006214884],"category_scores_gemma":[0.00003446535,0.00004733135,0.00002797296,0.001062647,0.00005842414,0.0105612,0.00003113213,0.0001609259,0.00001115436],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005642415,"about_ca_system_score_gemma":0.0002465674,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002996005,"about_ca_topic_score_gemma":0.000002435121,"domain_scores_codex":[0.9988558,0.00001283592,0.0003154096,0.00007700679,0.0005314751,0.0002074145],"domain_scores_gemma":[0.9992065,0.00001655364,0.0001676441,0.00009143783,0.0004322153,0.00008565441],"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":[0.0001395472,0.0001738797,0.003037608,0.0001598901,0.0000533225,0.00003345424,0.02595749,0.0073805,0.07429419,0.2918482,0.005398976,0.5915229],"study_design_scores_gemma":[0.003556987,0.001716158,0.04141077,0.0002731833,0.00003646417,0.001647758,0.00147853,0.8481844,0.03066504,0.009543923,0.06073173,0.000755042],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6256577,0.00003984083,0.3719709,0.0009903687,0.000145211,0.00006867829,5.97739e-7,0.0000360687,0.001090595],"genre_scores_gemma":[0.9982292,0.0002842063,0.001138054,0.000292237,0.00002686056,9.821907e-7,0.000001910932,0.000001722821,0.00002479911],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8408039,"threshold_uncertainty_score":0.7656612,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01159811356937183,"score_gpt":0.2353473477427224,"score_spread":0.2237492341733506,"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."}}