{"id":"W2995665739","doi":"10.1109/iccv.2019.00766","title":"Dual Adversarial Inference for Text-to-Image Synthesis","year":2019,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":34,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University; Concordia University","funders":"","keywords":"Inference; Computer science; Image (mathematics); Adversarial system; Artificial intelligence; Dual (grammatical number); Style (visual arts); Composition (language); Process (computing); Space (punctuation); Quality (philosophy); Image synthesis; Natural language processing; Information retrieval; Pattern recognition (psychology); Linguistics","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0003306954,0.0001965354,0.0002642166,0.0001062345,0.0001190056,0.0002730863,0.0007174178,0.00007112385,0.0004078371],"category_scores_gemma":[0.0004437392,0.0001653563,0.0001335705,0.0003073372,0.00002660497,0.0007399594,0.0003173982,0.00007084294,0.001128367],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000344356,"about_ca_system_score_gemma":0.00008850382,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004495246,"about_ca_topic_score_gemma":0.00001802961,"domain_scores_codex":[0.9984738,0.00006127691,0.0002317166,0.0005761405,0.0002295158,0.0004275507],"domain_scores_gemma":[0.9981725,0.0008152633,0.00006155643,0.0006242536,0.0001677419,0.000158671],"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":[0.0003004604,0.0004343592,0.001254639,0.00009923825,0.0003128106,0.00001928005,0.001817375,0.01645495,0.1585038,0.2651078,0.09600373,0.4596915],"study_design_scores_gemma":[0.001664978,0.0007202278,0.003413036,0.0000795056,0.00005433654,0.000008094045,0.0001888284,0.6426058,0.1823786,0.004853329,0.1625242,0.001509087],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002896148,0.000008015171,0.9772538,0.001557333,0.001001194,0.0006039811,0.00001003164,0.0001417764,0.01652775],"genre_scores_gemma":[0.6818655,0.000002396337,0.3149768,0.0006929669,0.0002748649,0.00007333352,0.00000136369,0.00001240157,0.002100324],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6789694,"threshold_uncertainty_score":0.9996493,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0130854788893676,"score_gpt":0.2495969254148634,"score_spread":0.2365114465254958,"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."}}