{"id":"W3213163682","doi":"10.1609/aaai.v35i2.16250","title":"Exploiting Relationship for Complex-scene Image Generation","year":2021,"lang":"en","type":"article","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":"Toronto Metropolitan University","funders":"","keywords":"Scene graph; Computer science; Generator (circuit theory); Artificial intelligence; Discriminator; Object (grammar); Generative grammar; Spatial relation; Image (mathematics); Computer vision; Semantics (computer science); Graph; Consistency (knowledge bases); Pattern recognition (psychology); 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":[],"consensus_categories":[],"category_scores_codex":[0.0004681661,0.0001717651,0.0002122571,0.00006147972,0.0004168707,0.0004001214,0.000831395,0.00006538102,0.00005509736],"category_scores_gemma":[0.001209409,0.0001420784,0.0001456288,0.0005049268,0.0001258591,0.0005793144,0.00023081,0.0001526677,0.00002609256],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003676981,"about_ca_system_score_gemma":0.0001088433,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008250041,"about_ca_topic_score_gemma":0.00001202945,"domain_scores_codex":[0.9984539,0.00003277138,0.0004716523,0.0004714072,0.0002930037,0.0002772709],"domain_scores_gemma":[0.9978101,0.0001985111,0.0003015246,0.000267157,0.001359947,0.00006275422],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001027919,0.00005978442,0.00007282227,0.00001661578,0.000009560836,2.511106e-7,0.0003825834,0.000301996,0.4072296,0.5659448,0.0006122331,0.02535947],"study_design_scores_gemma":[0.00002046371,0.00004089285,0.0001473207,0.00004453534,0.000008140126,0.000001993224,0.0002119961,0.3856525,0.5531003,0.06053464,0.0001246402,0.000112544],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01642003,0.00002311105,0.9706638,0.007178877,0.0004852287,0.0003560067,0.000008143898,0.00005890121,0.004805847],"genre_scores_gemma":[0.8434662,0.0000121718,0.1558022,0.0002523293,0.0001907227,0.00003841827,0.00000308033,0.00001011738,0.0002247697],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8270462,"threshold_uncertainty_score":0.5793791,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2131523915101248,"score_gpt":0.3214655293031366,"score_spread":0.1083131377930118,"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."}}