Zhonghua Xi
George Mason University
26 Papers
90 Citations
Zhonghua Xi is an academic researcher from George Mason University. The author has contributed to research in topics: Collision & Speaker diarisation. The author has an hindex of 11, co-authored 26 publications. Previous affiliations of Zhonghua Xi include Google.
Chat about Author
Papers
Ava Active Speaker: An Audio-Visual Dataset for Active Speaker Detection
Joseph Roth,Sourish Chaudhuri,Ondrej Klejch,Radhika Marvin,Andrew C. Gallagher,Liat Kaver,Sharadh Ramaswamy,Arkadiusz Stopczynski,Cordelia Schmid,Zhonghua Xi,Caroline Pantofaru +10 more
- 04 May 2020
TL;DR: The AVA Active Speaker dataset (AVA-ActiveSpeaker) as discussed by the authors contains temporally labeled face tracks in videos, where each face instance is labeled as speaking or not, and whether the speech is audible.
119
•Posted Content
AVA-ActiveSpeaker: An Audio-Visual Dataset for Active Speaker Detection
Joseph Roth,Sourish Chaudhuri,Ondrej Klejch,Radhika Marvin,Andrew C. Gallagher,Liat Kaver,Sharadh Ramaswamy,Arkadiusz Stopczynski,Cordelia Schmid,Zhonghua Xi,Caroline Pantofaru +10 more
TL;DR: This paper presents the AVA Active Speaker detection dataset (AVA-ActiveSpeaker), which has been publicly released to facilitate algorithm development and comparison, and introduces a state-of-the-art, jointly trained audio-visual model for real-time active speaker detection and compares several variants.
113
Computational wrapping: A universal method to wrap 3D-curved surfaces with nonstretchable materials for conformal devices.
Yu-Ki Lee,Zhonghua Xi,Young-Joo Lee,Yun-hyeong Kim,Yue Hao,Hongjin Choi,Myoung-Gyu Lee,Young-Chang Joo,Changsoon Kim,Jyh-Ming Lien,In-Suk Choi +10 more
TL;DR: It is demonstrated that the computational wrapping approach enables a design platform that can transform conventional nonstretchable 2D-based devices, such as electroluminescent lighting and flexible batteries, into conformal 3D curved devices.
45
Dual-Space Decomposition of 2D Complex Shapes
Guilin Liu,Zhonghua Xi,Jyh-Ming Lien +2 more
- 23 Jun 2014
TL;DR: A new decomposition method is proposed, called Dual-space Decomposition that handles complex 2D shapes by recognizing the importance of holes and classifying holes as either topological noise or structurally important features.
Learning to segment and unfold polyhedral mesh from failures
TL;DR: It is shown that the proposed method produces unfoldable segmentation that resembles carefully designed paper craft, and the key idea that enables this capability is an algorithm that learns from failed unfoldings.
29