{"id":"W2734498959","doi":"10.48550/arxiv.1709.07871","title":"FiLM: Visual Reasoning with a General Conditioning Layer","year":2017,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":189,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Affine transformation; Computer science; Benchmark (surveying); Feature (linguistics); Artificial intelligence; Transformation (genetics); Computation; Simple (philosophy); Artificial neural network; Layer (electronics); Image (mathematics); Task (project management); Process (computing); Pattern recognition (psychology); Machine learning; Algorithm; Mathematics; Engineering","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":[0.0006610155,0.00102828,0.0004500605,0.00032876,0.000274618,0.001287947,0.001865301,0.001101909,0.01354691],"category_scores_gemma":[0.002976926,0.0004916331,0.0006196535,0.0002622523,0.0009667533,0.003394955,0.002052416,0.002115168,0.002218924],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006640726,"about_ca_system_score_gemma":0.0006375542,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002051456,"about_ca_topic_score_gemma":0.002973128,"domain_scores_codex":[0.9996926,0.00005406551,0.00001683993,0.0001139302,0.00007843997,0.00004419943],"domain_scores_gemma":[0.9994597,0.0001677266,0.00005269947,0.0002166441,0.00006084976,0.00004241687],"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":[0.001012953,0.0004403288,0.001566121,0.0007074808,0.0002346323,0.000279288,0.0003226025,0.1391833,0.1123724,0.08695943,0.03264521,0.6242763],"study_design_scores_gemma":[0.00009902248,0.0001880886,0.0004797252,0.00004939901,0.00005807153,0.0001188006,0.00003236476,0.8702818,0.05922699,0.05626043,0.0131757,0.00002960549],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0208631,0.0004443693,0.9575563,0.0006042538,0.0001620012,0.00018521,0.0005561789,0.01103744,0.008591094],"genre_scores_gemma":[0.5194729,0.0003745376,0.4653334,0.0009391079,0.0001094962,0.000294098,0.001165952,0.001000593,0.01131],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01354691,"threshold_uncertainty_score":0.04531896,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05285417320652501,"score_gpt":0.2337116258580682,"score_spread":0.1808574526515432,"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."}}