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.
@article{arxiv.1511.04119,
title = {Action Recognition using Visual Attention},
author = {Shikhar Sharma and Ryan Kiros and Ruslan Salakhutdinov},
journal= {arXiv preprint arXiv:1511.04119},
year = {2016}
}