Abstract | ||
---|---|---|
Recent years have witnessed the popularity of using recurrent neural network (RNN) for action recognition in videos. However, videos are of high dimensionality and contain rich human dynamics with various motion scales, which makes the traditional RNNs difficult to capture complex action information. In this paper, we propose a novel recurrent spatial-temporal attention network (RSTAN) to address ... |
Year | DOI | Venue |
---|---|---|
2018 | 10.1109/TIP.2017.2778563 | IEEE Transactions on Image Processing |
Keywords | Field | DocType |
Videos,Feature extraction,Image recognition,Recurrent neural networks,Computer vision,Optical imaging,Three-dimensional displays | Computer vision,Data set,Action recognition,Popularity,Recurrent neural network,Human dynamics,Curse of dimensionality,Regularization (mathematics),Artificial intelligence,Mathematics | Journal |
Volume | Issue | ISSN |
27 | 3 | 1057-7149 |
Citations | PageRank | References |
13 | 0.69 | 37 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Wenbin Du | 1 | 37 | 1.75 |
Wang, Yali | 2 | 91 | 15.18 |
Yu Qiao | 3 | 2267 | 152.01 |