{"id":"W3011483492","doi":"10.1609/aaai.v35i3.16368","title":"Object-Centric Image Generation from Layouts","year":2021,"lang":"en","type":"preprint","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canadian Institute for Advanced Research; Université de Montréal","funders":"","keywords":"Computer science; Generator (circuit theory); Object (grammar); Artificial intelligence; Scene graph; Bounding overwatch; Fidelity; Minimum bounding box; Metric (unit); Computer vision; Image (mathematics); Similarity (geometry); Graph; Generative grammar; Theoretical computer science","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","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0004623938,0.0004855549,0.0005844802,0.0001402311,0.0002574165,0.001497073,0.003142291,0.0003016012,0.0001812118],"category_scores_gemma":[0.000537814,0.0003901911,0.0003491772,0.0006209129,0.0002217038,0.0005638215,0.00237671,0.0007968653,0.00006782011],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001026272,"about_ca_system_score_gemma":0.0003554247,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003407852,"about_ca_topic_score_gemma":0.0000520519,"domain_scores_codex":[0.9966683,0.00008050452,0.0008304151,0.001225919,0.0007548337,0.0004400723],"domain_scores_gemma":[0.9966932,0.0001064678,0.0008313023,0.0007699392,0.001474719,0.0001243808],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00006464015,0.0006388584,0.0001735502,0.0001077997,0.0002502827,0.000008829995,0.005107986,0.005770641,0.5604584,0.2851058,0.00332421,0.138989],"study_design_scores_gemma":[0.00002045498,0.00004359662,0.0001362512,0.0002778934,0.00003847156,0.000001120555,0.0002254063,0.3291166,0.6315696,0.03816768,0.00005643466,0.000346503],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1650573,0.0004203327,0.8113728,0.006668165,0.005541338,0.001178614,0.00006625815,0.0002101317,0.009485082],"genre_scores_gemma":[0.9632044,0.0002222537,0.03536228,0.0002798002,0.0006658244,0.00004722909,0.00001358372,0.00002431407,0.0001802504],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7981471,"threshold_uncertainty_score":0.999855,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07616563558512626,"score_gpt":0.278505073995008,"score_spread":0.2023394384098817,"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."}}