/action-recognition-visual-attention

Action recognition using soft attention based deep recurrent neural networks

Primary LanguageJupyter Notebook

Action Recognition using Visual Attention

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.

Dependencies

Input data format

This is provided in util/README.md

Reference

If you use this code as part of any published research, please acknowledge the following papers:

"Action Recognition using Visual Attention."
Shikhar Sharma, Ryan Kiros, Ruslan Salakhutdinov. arXiv

@article{sharma2015attention,
    title={Action Recognition using Visual Attention},
    author={Sharma, Shikhar and Kiros, Ryan and Salakhutdinov, Ruslan},
    journal={arXiv preprint arXiv:1511.04119},
    year={2015}
} 

"Show, Attend and Tell: Neural Image Caption Generation with Visual Attention."
Kelvin Xu, Jimmy Ba, Ryan Kiros, Kyunghyun Cho, Aaron Courville, Ruslan Salakhutdinov, Richard Zemel, Yoshua Bengio. To appear ICML (2015)

@article{Xu2015show,
    title={Show, Attend and Tell: Neural Image Caption Generation with Visual Attention},
    author={Xu, Kelvin and Ba, Jimmy and Kiros, Ryan and Cho, Kyunghyun and Courville, Aaron and Salakhutdinov, Ruslan and Zemel, Richard and Bengio, Yoshua},
    journal={arXiv preprint arXiv:1502.03044},
    year={2015}
}

License

This repsoitory is released under a revised (3-clause) BSD License. It is the implementation for our paper Action Recognition using Visual Attention. The repository uses some code from the project arctic-caption which is originally the implementation for the paper Show, Attend and Tell: Neural Image Caption Generation with Visual Attention and is also licensed under a revised (3-clause) BSD License.