{"id":"W2933890497","doi":"10.1109/iccv.2019.01040","title":"Tell, Draw, and Repeat: Generating and Modifying Images Based on Continual Linguistic Instruction","year":2019,"lang":"en","type":"preprint","venue":"","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canadian Institute for Advanced Research; Université de Montréal; University of Guelph; Vector Institute","funders":"Agence Nationale de la Recherche","keywords":"Computer science; Extension (predicate logic); Image (mathematics); Code (set theory); Simple (philosophy); Code generation; Artificial intelligence; Natural language processing; Computer vision; Programming language; Key (lock)","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000531218,0.0005912915,0.0003680068,0.0003204764,0.0003222027,0.0008986862,0.001579741,0.0008948505,0.007010843],"category_scores_gemma":[0.003474917,0.0003884731,0.0006638975,0.0001941371,0.0009835252,0.001635898,0.0009616677,0.0008714981,0.001343738],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005680077,"about_ca_system_score_gemma":0.0003630946,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002737832,"about_ca_topic_score_gemma":0.003278428,"domain_scores_codex":[0.9997724,0.00005947568,0.000008370103,0.00008304527,0.00005244417,0.00002433753],"domain_scores_gemma":[0.9990017,0.000570488,0.00007556265,0.0001971674,0.00008534147,0.00006981981],"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":[0.0008254803,0.0002909888,0.003060425,0.0003757402,0.0001431739,0.001093549,0.001796559,0.2427118,0.08247031,0.08096968,0.01365314,0.5726091],"study_design_scores_gemma":[0.00004098985,0.00009293323,0.0005392085,0.00001928839,0.00003650399,0.0002208287,0.00007512846,0.9359552,0.02615904,0.03091458,0.00591473,0.00003147795],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.116426,0.0003591329,0.8600701,0.0006317296,0.0001509412,0.0001378678,0.0002258283,0.008873508,0.01312474],"genre_scores_gemma":[0.7399437,0.000262433,0.242195,0.0002164496,0.00004171449,0.0001295218,0.000369524,0.001085698,0.01575595],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007010843,"threshold_uncertainty_score":0.02345359,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01344478684576166,"score_gpt":0.2737859628238873,"score_spread":0.2603411759781257,"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."}}