{"id":"W3146526033","doi":"10.48550/arxiv.2103.15812","title":"LatentKeypointGAN: Controlling Images via Latent Keypoints","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Artificial intelligence; Image (mathematics); Set (abstract data type); Matching (statistics); Pattern recognition (psychology); Computer vision; Position (finance); Generative adversarial network; Space (punctuation); Generative grammar; Domain (mathematical analysis); Mathematics","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003611229,0.000519867,0.0006816617,0.0002104654,0.0002729683,0.0005204727,0.001714371,0.0003362663,0.000123219],"category_scores_gemma":[0.00005385575,0.0005716129,0.0005367192,0.0004382194,0.0001235312,0.0007136792,0.002701999,0.0007141898,0.0001250867],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001971097,"about_ca_system_score_gemma":0.0002071045,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002691036,"about_ca_topic_score_gemma":0.00004979077,"domain_scores_codex":[0.996859,0.0003698306,0.0003506134,0.00166042,0.0001586372,0.0006014578],"domain_scores_gemma":[0.9973131,0.0001535794,0.0003466081,0.001505395,0.000416421,0.0002648503],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002897853,0.0001674085,0.001093178,0.00005693564,0.0004084032,0.001462613,0.0002641573,0.9882116,0.001551628,0.003765162,0.0006235217,0.002366355],"study_design_scores_gemma":[0.0007595718,0.00004204227,0.0009408003,0.0001386655,0.0001332081,0.00001211172,0.00004814124,0.9852413,0.004284419,0.007385663,0.0002973666,0.0007167241],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02750318,0.0003869137,0.9684148,0.0003663769,0.001557821,0.0003174497,0.00001171651,0.0002513958,0.001190384],"genre_scores_gemma":[0.9853567,0.0004532409,0.01186459,0.0002498149,0.0002411262,0.000001754306,0.0000258412,0.00003153369,0.001775393],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9578536,"threshold_uncertainty_score":0.9996735,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04725434967459104,"score_gpt":0.1714861754683885,"score_spread":0.1242318257937975,"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."}}