papers AI Learner
The Github is limit! Click to go to the new site.

CHAM: action recognition using convolutional hierarchical attention model

2017-05-19
Shiyang Yan, Jeremy S. Smith, Wenjin Lu, Bailing Zhang

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 convolutional 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 convolutional 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.

Abstract (translated by Google)
URL

https://arxiv.org/abs/1705.03146

PDF

https://arxiv.org/pdf/1705.03146


Similar Posts

Comments