{"id":"W2733512699","doi":"10.1145/3072959.3073674","title":"Facial retargeting with automatic range of motion alignment","year":2017,"lang":"en","type":"article","venue":"ACM Transactions on Graphics","topic":"Face recognition and analysis","field":"Computer Science","cited_by":60,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"National Research Foundation of Korea; Deutsche Forschungsgemeinschaft","keywords":"Retargeting; Computer science; Animation; Character animation; Facial motion capture; Artificial intelligence; Computer facial animation; Computer animation; Computer vision; Character (mathematics); Skeletal animation; Motion capture; Range (aeronautics); Computer graphics (images); Motion (physics); Polygon mesh; Pattern recognition (psychology); Facial recognition system; Mathematics; Face detection","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":[0.000188832,0.00009594037,0.0001426939,0.0001780848,0.0004769661,0.0001001272,0.0006096215,0.00004828379,0.00003673857],"category_scores_gemma":[0.00002563054,0.00008052446,0.0001210957,0.0002074395,0.00008331507,0.0003447543,0.000008040151,0.0001133304,0.00001319652],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001277131,"about_ca_system_score_gemma":0.00001931164,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004026398,"about_ca_topic_score_gemma":0.00006434732,"domain_scores_codex":[0.9991714,0.00003910159,0.0001689853,0.0001995464,0.000291837,0.0001291439],"domain_scores_gemma":[0.9988145,0.00004557634,0.0001582334,0.0008498749,0.00007793921,0.00005382362],"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":[0.00002816852,0.0007212429,0.005509399,0.0001344062,0.0004489947,0.00001596486,0.001579063,0.00151556,0.001136917,0.005241289,0.00005216941,0.9836168],"study_design_scores_gemma":[0.007116614,0.001594311,0.1255079,0.001105761,0.0009608823,0.0000641923,0.0007927139,0.7410117,0.08137806,0.03697452,0.001444865,0.002048478],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05320114,0.00001045963,0.9443222,0.001884574,0.0001007001,0.00009492505,0.000008354186,0.00008330487,0.0002943957],"genre_scores_gemma":[0.9763885,0.00005840111,0.02338996,0.00009445106,0.000007691509,0.00001205809,0.000001317821,0.000005399277,0.00004222585],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9815683,"threshold_uncertainty_score":0.3668486,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02607977643080836,"score_gpt":0.2548486290940474,"score_spread":0.228768852663239,"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."}}