Cascaded Temporal Spatial Features for Video Action Recognition
文献类型：会议论文
| 作者 | Tingzhao Yu1,2 ; Huxiang Gu1; Lingfeng Wang1; Shiming Xiang and1; Chunhong Pan1
|
| 出版日期 | 2017 |
| 会议日期 | 2017-9-17 |
| 会议地点 | Beijing, CHINA |
| 英文摘要 | Extracting spatial-temporal descriptors is a challenging task for video-based human action recognition. We decouple the 3D volume of video frames directly into a cascaded temporal spatial domain via a new convolutional architecture. The motivation behind this design is to achieve deep nonlinear feature representations with reduced network parameters. First, a 1D temporal network with shared parameters is first constructed to map the video sequences along the time axis into feature maps in temporal domain. These feature maps are then organized into channels like those of RGB image (named as Motion Image here for abbreviation), which is desired to preserve both temporal and spatial information. Second, the Motion Image is regarded as the input of the latter cascaded 2D spatial network. With the combination of the 1D temporal network and the 2D spatial network together, the size of whole network parameters is largely reduced. Benefiting from the Motion Image, our network is an end-to-end system for the task of action recognition, which can be trained with the classical algorithm of back propagation. Quantities of comparative experiments on two benchmark datasets demonstrate the effectiveness of our new architecture. |
| 源URL | [http://ir.ia.ac.cn/handle/173211/20351]  |
| 专题 | 自动化研究所_模式识别国家重点实验室_遥感图像处理团队 |
| 作者单位 | 1.National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences 2.School of Computer and Control Engineering, University of Chinese Academy of Sciences |
| 推荐引用方式 GB/T 7714 | Tingzhao Yu,Huxiang Gu,Lingfeng Wang,et al. Cascaded Temporal Spatial Features for Video Action Recognition[C]. 见:. Beijing, CHINA. 2017-9-17. |
入库方式： OAI收割
来源：自动化研究所
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。