Action Recognition using Visual Attention
neural information processing systems, Volume abs/1511.04119, 2015.
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 gli...More
PPT (Upload PPT)