{"id":"W2979930345","doi":"10.1109/cvpr.2019.01024","title":"Towards Natural and Accurate Future Motion Prediction of Humans and Animals","year":2019,"lang":"en","type":"article","venue":"","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":143,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"ENCODE; Computer science; Representation (politics); Set (abstract data type); Motion (physics); Object (grammar); Sequence (biology); Artificial intelligence; Term (time); Recurrent neural network; Natural (archaeology); Theoretical computer science; Artificial neural network","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":[],"consensus_categories":[],"category_scores_codex":[0.00008241073,0.00005460021,0.00007230007,0.00005946494,0.00004019628,0.00005729689,0.00005983989,0.00003795552,0.00004769603],"category_scores_gemma":[0.000002944588,0.000044101,0.0000151182,0.00007046524,0.00001388906,0.0005197058,0.00004274417,0.00005746378,0.000009731603],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000005723113,"about_ca_system_score_gemma":0.000007979786,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001071959,"about_ca_topic_score_gemma":0.000004337498,"domain_scores_codex":[0.9995642,0.00001851325,0.0001028479,0.0001595798,0.00008863543,0.00006625259],"domain_scores_gemma":[0.9997731,0.0000087256,0.00004811664,0.00009301814,0.00005201959,0.00002497135],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00004593918,0.0001246008,0.0153551,0.0002976249,0.000081399,0.000003688058,0.003569796,0.00001559082,0.1233001,0.1888791,0.002260109,0.6660669],"study_design_scores_gemma":[0.001079727,0.0003664828,0.9051638,0.00004563389,0.00001568561,0.00004108398,0.0004145967,0.05568684,0.02467164,0.01027698,0.002025833,0.0002117384],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9787076,0.0001333564,0.01698112,0.0002869588,0.0003568888,0.0001120786,0.000003837379,0.00006556048,0.003352586],"genre_scores_gemma":[0.9978518,0.00006500626,0.001640977,0.00007535049,0.00007463942,0.000001587508,0.000003866932,0.000002124022,0.0002846218],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8898087,"threshold_uncertainty_score":0.1798387,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01272171638934827,"score_gpt":0.2344414818072879,"score_spread":0.2217197654179396,"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."}}