Action Recognition using Visual Attention

Shikhar Sharma, Ryan Kiros, Ruslan Salakhutdinov


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.


  title     = {Action Recognition using Visual Attention},
  author    = {Sharma, Shikhar and
               Kiros, Ryan and
               Salakhutdinov, Ruslan},
  booktitle = {Neural Information Processing Systems (NIPS) Time Series Workshop},
  month     = {December},
  year      = {2015},
  url       = {}