{"id":"W2760103357","doi":"10.1609/aaai.v32i1.11671","title":"FiLM: Visual Reasoning with a General Conditioning Layer","year":2018,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":1633,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canadian Institute for Advanced Research; Université de Montréal","funders":"Fonds de recherche du Québec – Nature et technologies; CHIST-ERA; Nvidia","keywords":"Affine transformation; Computer science; Benchmark (surveying); Artificial intelligence; Feature (linguistics); Computation; Transformation (genetics); Artificial neural network; Simple (philosophy); Layer (electronics); Visual reasoning; Image (mathematics); Task (project management); Process (computing); Pattern recognition (psychology); Machine learning; Algorithm; Mathematics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0006397308,0.001068357,0.0004502192,0.0003313238,0.0002746774,0.001305957,0.001926961,0.001076341,0.01379259],"category_scores_gemma":[0.00284155,0.000518426,0.000651501,0.0002475681,0.0009339169,0.003454172,0.001959354,0.0021374,0.002281313],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000678196,"about_ca_system_score_gemma":0.0006646126,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002211309,"about_ca_topic_score_gemma":0.003112122,"domain_scores_codex":[0.9996909,0.00004986714,0.00001791759,0.0001119563,0.00008353875,0.00004590556],"domain_scores_gemma":[0.9994383,0.0001743177,0.00005448889,0.0002234226,0.00006621449,0.00004314872],"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":[0.001089078,0.0004489443,0.0014442,0.0007522595,0.0002412783,0.0002834982,0.0003204255,0.1298295,0.1252228,0.08001629,0.03318373,0.6271679],"study_design_scores_gemma":[0.0001144776,0.0002177195,0.0004922131,0.00005354484,0.00006839664,0.0001309734,0.0000334242,0.8590227,0.07309932,0.05123974,0.01549397,0.00003364491],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02013849,0.0004267631,0.9561568,0.0005475299,0.0001719791,0.0001998324,0.000560865,0.01305041,0.00874723],"genre_scores_gemma":[0.4952376,0.0003680628,0.4889565,0.0009619433,0.0001065531,0.000303953,0.001202365,0.001116639,0.01174642],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01379259,"threshold_uncertainty_score":0.04614073,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04609872896526987,"score_gpt":0.3260767922855972,"score_spread":0.2799780633203274,"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."}}