{"id":"W2940988007","doi":"10.1109/iccv.2019.00770","title":"Improved Conditional VRNNs for Video Prediction","year":2019,"lang":"en","type":"preprint","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canadian Institute for Advanced Research; Université de Montréal","funders":"","keywords":"Latent variable; Computer science; Probabilistic logic; Artificial intelligence; Generative model; Machine learning; Generative grammar; Latent variable model; Hierarchy; Sequence (biology); Conditional probability; Variable (mathematics); Sign (mathematics); Mathematics; Statistics","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":[0.000241168,0.0002093776,0.0002456727,0.00007354087,0.0001012461,0.0002695208,0.0006649832,0.0001670658,0.00007971196],"category_scores_gemma":[0.00005892173,0.0001853732,0.0002154831,0.00006008039,0.00005190669,0.0002839273,0.0006661724,0.0001983657,0.00003446365],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000601443,"about_ca_system_score_gemma":0.0002086229,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002008845,"about_ca_topic_score_gemma":0.000004792967,"domain_scores_codex":[0.9986302,0.00004664811,0.0002589965,0.0006644791,0.000165853,0.0002337994],"domain_scores_gemma":[0.9987519,0.0001634351,0.0001583923,0.000622171,0.0002392484,0.00006484507],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00007226541,0.0003041328,0.0002795983,0.0003730364,0.0007515101,0.000003533203,0.0003681122,0.3724463,0.0104073,0.1846953,0.398517,0.03178192],"study_design_scores_gemma":[0.0002895192,0.00006986503,0.0002208145,0.00002080674,0.00001896264,0.000001486713,0.000005106051,0.9616592,0.003110637,0.01935212,0.01504713,0.0002043655],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00005888083,0.00005630002,0.9924167,0.0008624156,0.003282509,0.0008498877,0.00021421,0.0001649478,0.002094155],"genre_scores_gemma":[0.5777985,0.0000184622,0.4134782,0.001372383,0.001658544,0.000412132,0.0004373218,0.00002738176,0.004797047],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5892129,"threshold_uncertainty_score":0.75593,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01896619644317105,"score_gpt":0.24357964108587,"score_spread":0.224613444642699,"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."}}