{"id":"W4386142017","doi":"10.1145/3606928","title":"Physics-based Motion Retargeting from Sparse Inputs","year":2023,"lang":"en","type":"article","venue":"Proceedings of the ACM on Computer Graphics and Interactive Techniques","topic":"Human Motion and Animation","field":"Engineering","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Retargeting; Avatar; Motion capture; Computer science; Human–computer interaction; Artificial intelligence; Kinematics; Motion (physics); Reinforcement learning; Computer vision; Robustness (evolution); Variety (cybernetics)","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":[0.0001214192,0.0001136077,0.0001192229,0.0001326208,0.0000620135,0.00005499334,0.0002714751,0.00004823628,0.0000047902],"category_scores_gemma":[0.0000460061,0.00009155627,0.00006543686,0.0002489192,0.00003667715,0.0001869134,0.0001349551,0.0001916457,0.000003245305],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001785424,"about_ca_system_score_gemma":0.000001820389,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005878353,"about_ca_topic_score_gemma":3.734307e-7,"domain_scores_codex":[0.9994875,0.000005446024,0.0001511043,0.0001417913,0.0001204211,0.00009370743],"domain_scores_gemma":[0.9996064,0.00005477127,0.00008378489,0.0001216219,0.0001116919,0.00002171012],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001262887,0.0002872325,0.02153726,0.0007150228,0.0002913295,0.000001622914,0.003783047,0.0005194819,0.6930179,0.05601157,0.05638526,0.167324],"study_design_scores_gemma":[0.0001511081,0.000117671,0.02593793,0.000577868,0.00001360681,4.443137e-7,0.00002483909,0.2645597,0.6711448,0.03620606,0.001076689,0.0001892362],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9856241,0.000006623825,0.01227104,0.0003681613,0.0001435994,0.0001775867,0.00000921672,0.0007532809,0.0006464441],"genre_scores_gemma":[0.9946662,0.00003563685,0.004940096,0.0001938694,0.0001198108,0.00001310136,0.000006942987,0.00001832044,0.000005986359],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2640403,"threshold_uncertainty_score":0.3733556,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0200134279654857,"score_gpt":0.2394402586501532,"score_spread":0.2194268306846675,"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."}}