{"id":"W2787964513","doi":"10.1016/j.imavis.2018.07.001","title":"Recurrent semi-supervised classification and constrained adversarial generation with motion capture data","year":2018,"lang":"en","type":"preprint","venue":"Image and Vision Computing","topic":"Human Motion and Animation","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"Polytechnique Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Adversarial system; Artificial intelligence; Motion capture; Task (project management); Generative grammar; Encoder; Machine learning; Cluster analysis; Animation; Motion (physics); Recurrent neural network; Decoding methods; Artificial neural network; Algorithm","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0003100808,0.0002219513,0.0001975668,0.00009848412,0.0001698671,0.0003236504,0.0001248504,0.0001786584,0.00002762239],"category_scores_gemma":[0.00003032906,0.0002052561,0.00001832138,0.00005882191,0.00007754398,0.0002664915,0.000240005,0.0003123228,0.000006406314],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003539054,"about_ca_system_score_gemma":0.00002216917,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007997603,"about_ca_topic_score_gemma":0.00001074872,"domain_scores_codex":[0.9988665,0.00006218969,0.0002881298,0.0004790016,0.0001661556,0.0001380039],"domain_scores_gemma":[0.9993314,0.0000266662,0.0001055977,0.0003467285,0.0001167524,0.00007281407],"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":[0.00009376809,0.0001380216,0.0007758148,0.001994648,0.0001927134,0.00001730993,0.005358633,0.009739626,0.07957286,0.0004225294,0.01560054,0.8860936],"study_design_scores_gemma":[0.0005220222,0.00003682743,0.003144395,0.0003114134,0.00003870354,0.00001362739,0.0001149566,0.9951008,0.0001477474,0.00004110596,0.0003020234,0.0002263864],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3837236,0.0002803602,0.613785,0.0001570374,0.0006588271,0.0003783009,0.00007688782,0.0002770634,0.0006628854],"genre_scores_gemma":[0.9842451,0.0001229939,0.01282821,0.00002831366,0.0008513138,0.000002571794,0.001885387,0.00002721917,0.000008853116],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9853612,"threshold_uncertainty_score":0.83701,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04916718987441594,"score_gpt":0.3028405284189153,"score_spread":0.2536733385444994,"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."}}