@inproceedings{14b85f1d89b14c60a8a695d8bb20c601,
title = "CHAM: Action recognition using convolutional hierarchical attention model",
abstract = "Recently, the soft attention mechanism, which was originally proposed in language processing, has been applied in computer vision tasks like image captioning. This paper presents improvements to the soft attention model by combining a con-volutional Long Short-Term Memory (LSTM) with a hierarchical system architecture to recognize action categories in videos. We call this model the Convolutional Hierarchical Attention Model (CHAM). The model applies a convolution-al operation inside the LSTM cell and an attention map generation process to recognize actions. The hierarchical architecture of this model is able to explicitly reason on multi-granularities of action categories. The proposed architecture achieved improved results on three publicly available datasets: the UCF sports dataset, the Olympic sports dataset and the HMDB51 dataset.",
keywords = "Action recognition, CNN, Convolutional LSTM, Hierarchical Architecture, Soft attention",
author = "Shiyang Yan and Smith, {Jeremy S.} and Wenjin Lu and Bailing Zhang",
note = "Publisher Copyright: {\textcopyright} 2017 IEEE.; 24th IEEE International Conference on Image Processing, ICIP 2017 ; Conference date: 17-09-2017 Through 20-09-2017",
year = "2017",
month = jul,
day = "2",
doi = "10.1109/ICIP.2017.8297025",
language = "English",
series = "Proceedings - International Conference on Image Processing, ICIP",
publisher = "IEEE Computer Society",
pages = "3958--3962",
booktitle = "2017 IEEE International Conference on Image Processing, ICIP 2017 - Proceedings",
}