Egocentric Gesture Recognition Using Recurrent 3D Convolutional Neural Networks with Spatiotemporal Transformer Modules

doi:10.1109/ICCV.2017.406

CORC > 自动化研究所 > 中国科学院自动化研究所 > 模式识别国家重点实验室 > 图像与视频分析团队

	Egocentric Gesture Recognition Using Recurrent 3D Convolutional Neural Networks with Spatiotemporal Transformer Modules
	Cao, Congqi1,2 ; Zhang, Yifan1,2 ; Wu, Yi 3,4; Lu, Hanqing1,2 ; Cheng, Jian1,2,5
	2017-10-22
会议日期	22-29 Oct. 2017
会议地点	Venice, Italy
DOI	10.1109/ICCV.2017.406
英文摘要	Gesture is a natural interface in interacting with wearable devices such as VR/AR helmet and glasses. The main challenge of gesture recognition in egocentric vision arises from the global camera motion caused by the spontaneous head movement of the device wearer. In this paper, we address the problem by a novel recurrent 3D convolutional neural network for end-to-end learning. We specially design a spatiotemporal transformer module with recurrent connections between neighboring time slices which can actively transform a 3D feature map into a canonical view in both spatial and temporal dimensions. To validate our method, we introduce a new dataset with sufficient size, variation and reality, which contains 83 gestures designed for interaction with wearable devices, and more than 24,000 RGB-D gesture samples from 50 subjects captured in 6 scenes. On this dataset, we show that the proposed network outperforms competing state-of-the-art algorithms. Moreover, our method can achieve state-of-the-art performance on the challenging GTEA egocentric action dataset.
内容类型	会议论文
源URL	[http://ir.ia.ac.cn/handle/173211/20890]
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
作者单位	1.National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences 2.University of Chinese Academy of Sciences 3.School of Technology, Nanjing Audit University 4.Department of Medicine, Indiana University, USA 5.CAS Center for Excellence in Brain Science and Intelligence Technology
推荐引用方式 GB/T 7714	Cao, Congqi,Zhang, Yifan,Wu, Yi,et al. Egocentric Gesture Recognition Using Recurrent 3D Convolutional Neural Networks with Spatiotemporal Transformer Modules[C]. 见:. Venice, Italy. 22-29 Oct. 2017.