Gesture Recognition using Spatiotemporal Deformable Convolutional Representation | |
Shi L(史磊)2,3; Zhang YF(张一帆)2,3; Hu J(胡静)1; Cheng J(程健)2,3; Lu HQ(卢汉清)2,3 | |
2019 | |
会议日期 | 22-25 Sept. 2019 |
会议地点 | 中国台湾 |
页码 | 1900-1904 |
英文摘要 | Dynamic gesture recognition, which plays an essential role in human-computer interaction, has been widely investigated but not yet addressed. The interference of the varied and complex background makes the classifier easily be misguided due to the relatively smaller size of the hands and arms compared with the full scenes. In this paper, we address the problem by proposing a novel spatiotemporal deformable convolutional neural network for end-to-end learning. To eliminate the background interference, a light-weight spatiotemporal deformable convolution module is specially designed to augment the spatiotemporal sampling locations of 3D convolution by learning additional offsets according to the preceding feature map. The proposed method is evaluated on two challenging datasets, EgoGesture and Jester, and achieves the state-of-the-art performance on both of the two datasets. The code and trained models will be released for better communication and future work. |
会议录出版者 | IEEE |
语种 | 英语 |
内容类型 | 会议论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/44375] |
专题 | 自动化研究所_模式识别国家重点实验室_图像与视频分析团队 |
通讯作者 | Zhang YF(张一帆) |
作者单位 | 1.Power Research Institute of State Gride, Jiangxi Electric Power Company 2.National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences 3.University of Chinese Academy of Sciences |
推荐引用方式 GB/T 7714 | Shi L,Zhang YF,Hu J,et al. Gesture Recognition using Spatiotemporal Deformable Convolutional Representation[C]. 见:. 中国台湾. 22-25 Sept. 2019. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
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。
修改评论