@inproceedings{sharma2016action,
author = {Sharma, Shikhar and Kiros, Ryan and Salakhutdinov, Ruslan},
title = {Action Recognition using Visual Attention},
booktitle = {International Conference on Learning Representations (ICLR) Workshop},
year = {2016},
month = {May},
abstract = {We propose a soft attention based model for the task of action recognition in videos. We use multi-layered Recurrent Neural Networks (RNNs) with Long Short-Term Memory (LSTM) units which are deep both spatially and temporally. Our model learns to focus selectively on parts of the video frames and classifies videos after taking a few glimpses. The model essentially learns which parts in the frames are relevant for the task at hand and attaches higher importance to them. We evaluate the model on UCF-11 (YouTube Action), HMDB-51 and Hollywood2 datasets and analyze how the model focuses its attention depending on the scene and the action being performed.},
url = {http://approjects.co.za/?big=en-us/research/publication/action-recognition-using-visual-attention-2/},
}