{"id":"W2963398599","doi":"10.1109/cvpr.2016.500","title":"Ask Me Anything: Free-Form Visual Question Answering Based on Knowledge from External Sources","year":2016,"lang":"en","type":"preprint","venue":"","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":368,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Question answering; Computer science; Image (mathematics); Information retrieval; Knowledge base; Ask price; Representation (politics); Artificial intelligence; Knowledge representation and reasoning; Natural language; Questions and answers; Natural language processing","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00205934,0.001779751,0.001035149,0.001940762,0.000702317,0.002041579,0.003509652,0.003174398,0.008840864],"category_scores_gemma":[0.009059206,0.0005754305,0.001683058,0.0009942789,0.001238486,0.006028608,0.00317029,0.002356916,0.002742514],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001313304,"about_ca_system_score_gemma":0.001080573,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008442337,"about_ca_topic_score_gemma":0.008949405,"domain_scores_codex":[0.9981681,0.0006392327,0.00009238483,0.0006369841,0.0003249534,0.00013836],"domain_scores_gemma":[0.9964898,0.002168948,0.0002085441,0.000559866,0.0004203219,0.0001524729],"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":[0.0008793915,0.0009025443,0.004316508,0.001992815,0.0003212105,0.0008115704,0.003168538,0.05223382,0.04023241,0.04263968,0.05793997,0.7945615],"study_design_scores_gemma":[0.0001480826,0.0002351719,0.002105511,0.0001626622,0.0001754222,0.0004268425,0.0006276321,0.8318028,0.02190738,0.1125866,0.02972427,0.00009748845],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02766516,0.001328002,0.9449382,0.001530613,0.0001381907,0.0005558711,0.002472258,0.0123185,0.009053255],"genre_scores_gemma":[0.4302499,0.0005259383,0.546946,0.00123314,0.000236717,0.0008350798,0.009857893,0.0005380867,0.009577236],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008840864,"threshold_uncertainty_score":0.02957565,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01567864347003803,"score_gpt":0.3060882820700778,"score_spread":0.2904096386000397,"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."}}