{"id":"W2964501821","doi":"10.1109/crv.2019.00018","title":"Hierarchically-Fused Generative Adversarial Network for Text to Realistic Image Synthesis","year":2019,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Computer science; Discriminator; Exploit; Artificial intelligence; Image (mathematics); Similarity (geometry); Image synthesis; Adversarial system; Generative adversarial network; Generative grammar; Scheme (mathematics); Scale (ratio); Pattern recognition (psychology); Network architecture","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":[0.0006261415,0.0003332316,0.0004849345,0.0001107387,0.0002806742,0.0003775121,0.001108402,0.0001159557,0.0003755253],"category_scores_gemma":[0.0004758951,0.0002799749,0.0002312201,0.0005428111,0.00005448629,0.0005255342,0.0003675055,0.0001381921,0.0005165546],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007751981,"about_ca_system_score_gemma":0.0001366344,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008937703,"about_ca_topic_score_gemma":0.0000666999,"domain_scores_codex":[0.99733,0.0002308456,0.0004141484,0.0009259948,0.0003279914,0.0007710956],"domain_scores_gemma":[0.9971316,0.001291565,0.000111433,0.0009125944,0.0002556469,0.0002971004],"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":[0.0005821497,0.0002894192,0.0002439479,0.00006402519,0.0004442705,0.00002378457,0.001368225,0.1516094,0.05585038,0.3377571,0.3480237,0.1037436],"study_design_scores_gemma":[0.001563489,0.0007075925,0.001063775,0.00008451909,0.00007892173,0.000007055514,0.00007041815,0.8806245,0.02713381,0.01498149,0.07235464,0.001329755],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0008745158,0.00002131463,0.978995,0.004422376,0.001395153,0.001173029,0.00003023897,0.000183251,0.01290517],"genre_scores_gemma":[0.2206831,0.000007097879,0.7719885,0.002703625,0.001347327,0.0002286667,0.00001037008,0.00003572452,0.002995709],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7290151,"threshold_uncertainty_score":0.9999653,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01068398522088379,"score_gpt":0.2372953983253776,"score_spread":0.2266114131044938,"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."}}