{"id":"W2174492417","doi":"10.48550/arxiv.1511.05960","title":"ABC-CNN: An Attention Based Convolutional Neural Network for Visual Question Answering","year":2015,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":278,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Convolutional neural network; Question answering; Computer science; Artificial intelligence; Visual attention; Natural language processing; Pattern recognition (psychology); Psychology; Neuroscience; Cognition","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006072483,0.0002829709,0.0002485923,0.0001770285,0.0003264047,0.0001560817,0.001114449,0.0002593742,0.000009537492],"category_scores_gemma":[0.00005393492,0.0003616142,0.0001723624,0.0003976646,0.00008414117,0.0004656004,0.0005704619,0.0004974554,0.00003365419],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003264789,"about_ca_system_score_gemma":0.0002738279,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005470171,"about_ca_topic_score_gemma":0.00006755615,"domain_scores_codex":[0.9979219,0.0002549743,0.0002188206,0.001100764,0.0001272713,0.0003762988],"domain_scores_gemma":[0.9981185,0.0001322763,0.0003026957,0.0008020978,0.0004075805,0.0002368961],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003530966,0.00008801043,0.01209403,0.0000315068,0.00002016596,0.000006445151,0.00002412599,0.9044352,0.00005246185,0.08226984,0.0001545192,0.0007883992],"study_design_scores_gemma":[0.0005545948,0.0001058237,0.03855866,0.00004512476,0.00004234132,0.000001810433,0.000007294917,0.940523,0.000005287149,0.01956489,0.0002456321,0.0003456037],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3418358,0.00001475883,0.6566499,0.0001829101,0.0004376906,0.0004053479,0.00001557245,0.0003594302,0.00009863407],"genre_scores_gemma":[0.9685286,0.00000262812,0.0304556,0.00009486452,0.000343492,0.00001263759,0.0003600616,0.00002373984,0.0001784003],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6266928,"threshold_uncertainty_score":0.9998836,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07866269093093313,"score_gpt":0.2518239291440776,"score_spread":0.1731612382131444,"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."}}