TY  - CONF
AU  - Alvaro Peris
AU  - Marc Bolaños
AU  - Petia Radeva
AU  - Francisco Casacuberta
A2  - ICANN
PY  - 2016//
TI  - Video Description Using Bidirectional Recurrent Neural Networks
BT  - 25th International Conference on Artificial Neural Networks
SP  - 3
EP  - 11
VL  - 2
KW  - Video description
KW  - Neural Machine Translation
KW  - Birectional Recurrent Neural Networks
KW  - LSTM
KW  - Convolutional Neural Networks
N2  - Although traditionally used in the machine translation field, the encoder-decoder framework has been recently applied for the generation of video and image descriptions. The combination of Convolutional and Recurrent Neural Networks in these models has proven to outperform the previous state of the art, obtaining more accurate video descriptions. In this work we propose pushing further this model by introducing two contributions into the encoding stage. First, producing richer image representations by combining object and location information from Convolutional Neural Networks and second, introducing Bidirectional Recurrent Neural Networks for capturing both forward and backward temporal relationships in the input frames.
L1  - http://refbase.cvc.uab.es/files/PBR2016.pdf
N1  - MILAB;
ID  - Alvaro Peris2016
ER  -