{"id":"W3215649702","doi":"10.1016/j.patcog.2021.108439","title":"3D pose estimation and future motion prediction from 2D images","year":2021,"lang":"en","type":"article","venue":"Pattern Recognition","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Guelph; University of Alberta","funders":"","keywords":"Benchmark (surveying); Computer science; Kinematics; Pose; Artificial intelligence; Encoder; Motion capture; Task (project management); Projection (relational algebra); Sequence (biology); Motion (physics); Motion estimation; Representation (politics); RGB color model; Computer vision; Encoding (memory); Algorithm","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002482649,0.001310827,0.0008628162,0.001478493,0.0002999033,0.0007526266,0.0007148996,0.0007920861,0.003115369],"category_scores_gemma":[0.0009915436,0.0008273784,0.0008407687,0.00111509,0.0003052456,0.0008338836,0.0007563165,0.0008193295,0.002836601],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003204654,"about_ca_system_score_gemma":0.0005846936,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007186762,"about_ca_topic_score_gemma":0.0146978,"domain_scores_codex":[0.9997504,0.00002009552,0.0000121935,0.00008995792,0.00008622611,0.00004112906],"domain_scores_gemma":[0.9997613,0.00003714062,0.00004257859,0.0000516722,0.00008021494,0.00002714833],"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":[0.0004352586,0.0002105751,0.01632146,0.0001635032,0.000132463,0.0004511283,0.0001449618,0.1349164,0.1102642,0.001856699,0.008138316,0.7269652],"study_design_scores_gemma":[0.00001336506,0.0001206259,0.01535599,0.00003686562,0.00003965804,0.0004356728,0.00005652764,0.948253,0.02902197,0.002860129,0.003766384,0.00003985843],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03845639,0.0004864349,0.9553371,0.0001762168,0.0001604136,0.0000872879,0.001045861,0.002468884,0.001781414],"genre_scores_gemma":[0.5674971,0.001211962,0.4216191,0.000223675,0.0001796258,0.0001605413,0.002955579,0.0004031026,0.005749341],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007186762,"threshold_uncertainty_score":0.01428986,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01518293046901832,"score_gpt":0.2254038673814595,"score_spread":0.2102209369124412,"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."}}