DTA:Double LSTM with Temporal-wise Attention Network for Action Recognition
文献类型：会议论文
| 作者 | Yangyang Xu; Lei Wang; Jun Cheng; Haiying Xia; Jianqin Yin |
| 出版日期 | 2017 |
| 会议地点 | 中国成都 |
| 英文摘要 | In this paper, we propose a new architecture for human action recognition by using a convolution neural networks (CNN) and two Long Short-Term Memory(LSTM) networks with temporal-wise attention model. We call this network the Double LSTM with Temporal-wise Attention network (DTA). The features extracted by our model are both spatially and temporally. The attention model can learn which parts in which frames in a video are relevant to the video label and pay more attention on them. We designed a joint optimization layer (JOL) to jointly process two kinds of feature produced by two LSTMs. The proposed networks achieved improved performance on three widely used datasets--- the UCF Sports dataset, the UCF11 dataset and the HMDB51 dataset. |
| 语种 | 英语 |
| 源URL | [http://ir.siat.ac.cn:8080/handle/172644/11833]  |
| 专题 | 深圳先进技术研究院_集成所 |
| 作者单位 | 2017 |
| 推荐引用方式 GB/T 7714 | Yangyang Xu,Lei Wang,Jun Cheng,et al. DTA:Double LSTM with Temporal-wise Attention Network for Action Recognition[C]. 见:. 中国成都. |
入库方式： OAI收割
来源：深圳先进技术研究院
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。