{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002208283,0.0002332453,0.0001919065,0.0001855853,0.0005952262,0.0007630513,0.0006588329,0.0002678931,0.00007666022],"category_scores_gemma":[0.00001592591,0.0002247486,0.0001469131,0.00004320494,0.00002845444,0.0004335238,0.0005536614,0.0006956055,0.0000295932],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001342794,"about_ca_system_score_gemma":0.00002484645,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005584625,"about_ca_topic_score_gemma":0.00001230224,"domain_scores_codex":[0.9984708,0.00009398054,0.000289655,0.0006375482,0.0002828554,0.0002251058],"domain_scores_gemma":[0.9985256,0.00001953307,0.000360627,0.0009015108,0.000109473,0.00008322387],"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":[0.00001872685,0.0005112165,0.0004113558,0.0001390685,0.0001130617,0.00003080475,0.0003008467,0.2903336,0.0002373677,0.03601145,0.008581644,0.6633109],"study_design_scores_gemma":[0.0001552684,0.00007195612,0.001654154,0.0001628032,0.0000170018,0.000007352827,0.000001848398,0.9832402,0.0001295155,0.01425187,0.00009931462,0.0002086563],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08831944,0.00002525075,0.8978854,0.0001552655,0.005907774,0.0003380164,0.000007698626,0.0004414241,0.006919672],"genre_scores_gemma":[0.9972481,0.00001822481,0.001265588,0.0001308044,0.0009002414,0.00002048224,0.0001202146,0.0000139611,0.0002823915],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9089286,"threshold_uncertainty_score":0.9164982,"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."}}