{"id":"W2010071870","doi":"10.1007/s00371-012-0678-z","title":"Latent motion spaces for full-body motion editing","year":2012,"lang":"en","type":"article","venue":"The Visual Computer","topic":"Human Motion and Animation","field":"Engineering","cited_by":5,"is_retracted":false,"has_abstract":false,"ca_institutions":"Kingston Health Sciences Centre","funders":"Coordenação de Aperfeiçoamento de Pessoal de Nível Superior; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; École Polytechnique Fédérale de Lausanne","keywords":"Computer science; Motion interpolation; Motion capture; Motion (physics); Computer vision; Interpolation (computer graphics); Inverse kinematics; Artificial intelligence; Key frame; Kinematics; Motion estimation; Computer graphics; Frame (networking); Trajectory; Animation; Computer graphics (images); Block-matching algorithm; Video tracking","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":[0.0002150791,0.0000776637,0.00006315142,0.00003812878,0.00009450852,0.00005151932,0.00005151166,0.00003356427,0.00004537303],"category_scores_gemma":[0.000004113812,0.0000589805,0.00004170627,0.00004784808,0.000009519324,0.0001845263,0.00001574977,0.0000618388,0.0001253863],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002733809,"about_ca_system_score_gemma":8.779357e-7,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":9.66679e-7,"about_ca_topic_score_gemma":6.081191e-7,"domain_scores_codex":[0.9995564,0.00002211324,0.0001098651,0.00005884037,0.00008150301,0.0001712371],"domain_scores_gemma":[0.9998276,0.00002623739,0.00002422508,0.0000617777,0.00002476925,0.00003538886],"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":[0.00006146288,0.0006385139,0.005076156,0.0008696672,0.0003041317,0.000001215399,0.01389527,0.2159887,0.09692007,0.05300206,0.05903392,0.5542088],"study_design_scores_gemma":[0.0001953158,0.00005115427,0.01570297,0.00001911092,0.00001197198,0.000003264411,0.00003084444,0.9789243,0.001837237,0.0001321155,0.002992875,0.00009877721],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4214447,0.0000229762,0.5770503,0.00009075287,0.000962443,0.0001197053,0.000001233111,0.0001814994,0.0001263761],"genre_scores_gemma":[0.9956809,0.0000023422,0.00120723,0.00005832322,0.002954678,0.00001144778,0.00002283445,0.00001660944,0.00004564112],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7629356,"threshold_uncertainty_score":0.2405155,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02401583510250719,"score_gpt":0.2683020816247672,"score_spread":0.24428624652226,"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."}}