{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004328714,0.001280838,0.0004830661,0.0007202059,0.0003079529,0.0006717303,0.001855477,0.001311234,0.005142367],"category_scores_gemma":[0.00138577,0.0003508061,0.0007338519,0.0007255144,0.0004727645,0.001645046,0.001068856,0.001469803,0.00149482],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001563393,"about_ca_system_score_gemma":0.001034121,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02656222,"about_ca_topic_score_gemma":0.0357933,"domain_scores_codex":[0.9997326,0.00003919641,0.00001129216,0.0001104702,0.00005443299,0.00005198343],"domain_scores_gemma":[0.9996561,0.0001013367,0.00002876443,0.00006896905,0.0001146135,0.00003022203],"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":[0.0004566159,0.0004362787,0.005084494,0.0006280658,0.000238824,0.0003093976,0.0002702696,0.1040762,0.05309794,0.01855166,0.07851823,0.738332],"study_design_scores_gemma":[0.00003471009,0.0001118201,0.00154959,0.00004492843,0.00006191425,0.00011683,0.00004240902,0.9514227,0.01505206,0.01710245,0.01443607,0.00002453229],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09505685,0.005729004,0.8430711,0.001847485,0.000629882,0.000578391,0.006278602,0.02420368,0.02260497],"genre_scores_gemma":[0.6778176,0.001644334,0.2834142,0.001971014,0.0001795138,0.0004137194,0.0129365,0.000449566,0.0211735],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02656222,"threshold_uncertainty_score":0.0528152,"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."}}