PT Unknown
AU Marc Bolaños
   Alvaro Peris
   Francisco Casacuberta
   Petia Radeva
TI VIBIKNet: Visual Bidirectional Kernelized Network for Visual Question Answering
BT 8th Iberian Conference on Pattern Recognition and Image Analysis
PY 2017
DI 10.1007/978-3-319-58838-4_41
DE Visual Qestion Aswering; Convolutional Neural Networks; Long short-term memory networks
AB In this paper, we address the problem of visual question answering by proposing a novel model, called VIBIKNet. Our model is based on integrating Kernelized Convolutional Neural Networks and Long-Short Term Memory units to generate an answer given a question about an image. We prove that VIBIKNet is an optimal trade-off between accuracy and computational load, in terms of memory and time consumption. We validate our method on the VQA challenge dataset and compare it to the top performing methods in order to illustrate its performance and speed.
ER