{"id":"W4391265509","doi":"10.54097/fg717x36","title":"Character Motion Synthesis Based on Deep Learning: A Survey","year":2023,"lang":"en","type":"article","venue":"Highlights in Science Engineering and Technology","topic":"Human Motion and Animation","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Arts Foundation; University of Toronto","funders":"","keywords":"Character (mathematics); Artificial intelligence; Motion (physics); Computer vision; Deep learning; Computer science; Psychology; Mathematics; Geometry","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":[0.0005006744,0.00009868529,0.0001055547,0.001468195,0.00008230946,0.00003302775,0.0001284727,0.00009156,0.00001006221],"category_scores_gemma":[0.0002947217,0.00009355367,0.000009676924,0.001886646,0.00008101151,0.0001029893,0.00001848864,0.0001703941,0.0002513703],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005391455,"about_ca_system_score_gemma":0.000005798035,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001704855,"about_ca_topic_score_gemma":0.000004914833,"domain_scores_codex":[0.9992904,0.00001120579,0.0001193558,0.000197026,0.0001299542,0.0002520764],"domain_scores_gemma":[0.9997208,0.00008200858,0.00001200893,0.0001236706,0.00002315921,0.00003836984],"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":[0.000005567671,0.00004315273,0.009779346,0.00009761175,0.00000697894,0.00003150115,0.0002841379,0.8350244,0.0932084,0.03076049,0.0001128494,0.03064559],"study_design_scores_gemma":[0.00007897313,0.00001879323,0.1206567,0.00003839497,9.110499e-7,0.000001393853,0.00001048241,0.866823,0.01072539,0.0000335853,0.001501858,0.0001105647],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9937145,0.00001504353,0.003598227,0.0003306299,0.0002582353,0.00006803295,0.000001671001,0.001694409,0.0003193185],"genre_scores_gemma":[0.9996515,0.00004867664,0.0002152585,0.000004365298,0.00001615018,0.00002446252,0.000003354025,0.0000135747,0.00002266556],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1108774,"threshold_uncertainty_score":0.3815008,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01081884612649964,"score_gpt":0.2092216287341003,"score_spread":0.1984027826076007,"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."}}