TY  - CONF
AU  - Marc Bolaños
AU  - Alvaro Peris
AU  - Francisco Casacuberta
AU  - Petia Radeva
A2  - IbPRIA
PY  - 2017//
TI  - VIBIKNet: Visual Bidirectional Kernelized Network for Visual Question Answering
BT  - 8th Iberian Conference on Pattern Recognition and Image Analysis
KW  - Visual Qestion Aswering
KW  - Convolutional Neural Networks
KW  - Long short-term memory networks
N2  - 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.
L1  - http://refbase.cvc.uab.es/files/BPC2017.pdf
UR  - http://dx.doi.org/10.1007/978-3-319-58838-4_41
N1  - MILAB; no proj
ID  - Marc Bolaños2017
ER  -