{"id":"W2614034469","doi":"10.1109/cvpr.2017.497","title":"On Human Motion Prediction Using Recurrent Neural Networks","year":2017,"lang":"en","type":"preprint","venue":"","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":111,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Nvidia","keywords":"Computer science; Recurrent neural network; Artificial intelligence; Motion (physics); Intersection (aeronautics); Deep learning; Motion capture; Computer graphics; Machine learning; Focus (optics); Artificial neural network; Scalability; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000770672,0.00108615,0.0007526037,0.0005732341,0.0002080229,0.0004824435,0.001067181,0.0009197144,0.001604622],"category_scores_gemma":[0.003321463,0.0004482861,0.0004932925,0.0005932816,0.000464323,0.001159967,0.0006877748,0.0009536916,0.0005924889],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006111632,"about_ca_system_score_gemma":0.0004998497,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01233836,"about_ca_topic_score_gemma":0.01178353,"domain_scores_codex":[0.9997053,0.00007915719,0.00001304826,0.0001027947,0.00006135947,0.00003838942],"domain_scores_gemma":[0.9993238,0.0003764056,0.00006492282,0.0000727357,0.0001314646,0.00003057584],"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":[0.000185475,0.00005054989,0.000943843,0.00008128947,0.00008383214,0.00008414227,0.00005034859,0.7991619,0.005302198,0.005192944,0.003161694,0.1857018],"study_design_scores_gemma":[0.000002029201,0.000009984564,0.0001222617,0.000004414491,0.000004058954,0.000007486392,0.00000163204,0.9977785,0.0005024116,0.001391711,0.0001729294,0.000002590936],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05426871,0.002780169,0.9369214,0.0007158666,0.0001832542,0.00003740656,0.0003142125,0.001685544,0.00309342],"genre_scores_gemma":[0.8619229,0.002417939,0.1262342,0.0004019263,0.0003103369,0.00007775655,0.001083421,0.0002021147,0.007349405],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01233836,"threshold_uncertainty_score":0.02453309,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1107457646655718,"score_gpt":0.3375585825144476,"score_spread":0.2268128178488758,"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."}}