{"id":"W2904851806","doi":"10.1016/j.asoc.2019.105511","title":"Adversarial autoencoders with constant-curvature latent manifolds","year":2019,"lang":"en","type":"article","venue":"Applied Soft Computing","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":29,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Manitoba","funders":"Canada Excellence Research Chairs, Government of Canada; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; Nvidia","keywords":"Discriminator; Embedding; Computer science; MNIST database; Autoencoder; Euclidean geometry; Artificial intelligence; Probabilistic logic; Constant (computer programming); Algorithm; Constant curvature; Mathematics; Curvature; Pattern recognition (psychology); Deep learning; Geometry","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":[0.0001767895,0.0001725828,0.0001834236,0.00008341371,0.0001889924,0.0001778905,0.0003774872,0.00008714206,0.00005156401],"category_scores_gemma":[0.000003010889,0.0001511135,0.00004720723,0.0002509964,0.00003235422,0.0002085842,0.0001473908,0.0002378312,0.0004844207],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004315859,"about_ca_system_score_gemma":0.00007754729,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008714377,"about_ca_topic_score_gemma":0.000003651904,"domain_scores_codex":[0.9987108,0.00002208322,0.000197877,0.0004489411,0.0002907877,0.0003294744],"domain_scores_gemma":[0.9993116,0.00009408791,0.0001381221,0.0003191303,0.00005828009,0.000078766],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002013116,0.000354717,0.004160534,0.0001916332,0.00043176,0.000130989,0.006807732,0.05341056,0.006665006,0.7257898,0.004777156,0.1970788],"study_design_scores_gemma":[0.007529774,0.0004900424,0.005416958,0.0003317299,0.00008576916,0.0002103408,0.0007231401,0.9408691,0.004359812,0.01075299,0.02718769,0.002042665],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.135301,0.00002296008,0.8149272,0.0003266602,0.000818643,0.0004760469,0.000001761446,0.0006848339,0.04744091],"genre_scores_gemma":[0.9670185,0.000001916158,0.03188191,0.0008143349,0.000116795,0.000003367293,0.000009375417,0.00001383197,0.0001398913],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8874585,"threshold_uncertainty_score":0.622641,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007320489895778125,"score_gpt":0.1978749654289738,"score_spread":0.1905544755331956,"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."}}