Match!
Wei Yang
University of Science and Technology of China
Data miningComputer networkComputer securityComputer scienceTheoretical computer science
142Publications
15H-index
929Citations
What is this?
Publications 135
Newest
#1Zhenbo Xu (USTC: University of Science and Technology of China)H-Index: 2
#2Wei ZhangH-Index: 2
Last. Liusheng HuangH-Index: 28
view all 8 authors...
Current multi-object tracking and segmentation (MOTS) methods follow the tracking-by-detection paradigm and adopt convolutions for feature extraction. However, as affected by the inherent receptive field, convolution based feature extraction inevitably mixes up the foreground features and the background features, resulting in ambiguities in the subsequent instance association. In this paper, we propose a highly effective method for learning instance embeddings based on segments by converting the...
1 Citations
#1Zhenbo XuH-Index: 2
#2Wei ZhangH-Index: 2
Last. Liusheng HuangH-Index: 7
view all 10 authors...
Multiple-object tracking and segmentation (MOTS) is a novel computer vision task that aims to jointly perform multiple object tracking (MOT) and instance segmentation. In this work, we present PointTrack++, an effective on-line framework for MOTS, which remarkably extends our recently proposed PointTrack framework. To begin with, PointTrack adopts an efficient one-stage framework for instance segmentation, and learns instance embeddings by converting compact image representations to un-ordered 2...
May 1, 2020 in ICASSP (International Conference on Acoustics, Speech, and Signal Processing)
#1Bangzhou Xin (USTC: University of Science and Technology of China)H-Index: 1
#2Wei Yang (USTC: University of Science and Technology of China)H-Index: 15
Last. Liusheng Huang (USTC: University of Science and Technology of China)H-Index: 28
view all 6 authors...
Source
Apr 1, 2020 in VLDB (Very Large Data Bases)
#1Shaowei Wang (Tencent)H-Index: 1
#2Yuqiu Qian (Tencent)
Last. Hongli Xu (USTC: University of Science and Technology of China)H-Index: 17
view all 6 authors...
Source
Feb 7, 2020 in AAAI (National Conference on Artificial Intelligence)
#1Zhenbo Xu (USTC: University of Science and Technology of China)H-Index: 2
#2Wei Zhang (Baidu)H-Index: 2
Last. Liusheng Huang (USTC: University of Science and Technology of China)H-Index: 7
view all 9 authors...
3D object detection is an essential task in autonomous driving and robotics. Though great progress has been made, challenges remain in estimating 3D pose for distant and occluded objects. In this paper, we present a novel framework named ZoomNet for stereo imagery-based 3D detection. The pipeline of ZoomNet begins with an ordinary 2D object detection model which is used to obtain pairs of left-right bounding boxes. To further exploit the abundant texture cues in rgb images for more accurate disp...
6 CitationsSource
Source
#1Shaowei Wang (USTC: University of Science and Technology of China)H-Index: 7
#2Liusheng Huang (USTC: University of Science and Technology of China)H-Index: 28
Last. Wei Yang (USTC: University of Science and Technology of China)H-Index: 15
view all 7 authors...
For the purpose of improving the quality of services, softwares or online services are collecting various of user data, such as personal information and locations. Such data facilitates mining statistical knowledge of users, but threatens users’ privacy as it may reveal sensitive information (e.g., identities and activities) about individuals. This work considers distribution estimation over user-contributed data meanwhile providing rigid protection of their data with local \epsilon-different...
7 CitationsSource
The Byzantine General Problem is a well-known problem in distributed systems, Fitzi et al. (Phys Rev Lett 87(21):217901, 2001) and Gaertner et al. (Phys Rev Lett 100(7):070504, 2008) proposed slightly weaker 3-players Byzantine protocols using quantum entanglement, respectively. However, these protocols are difficult to be applied to the n-players situation, since they require a lot of complicated entangled quantum resources, and more seriously, they all face the risk of being attacked. In this ...
Source
#1Shaowei Wang (Tencent)H-Index: 1
#2Jiachun DuH-Index: 1
Last. Hongli XuH-Index: 17
view all 8 authors...
Voting plays a central role in bringing crowd wisdom to collective decision making, meanwhile data privacy has been a common ethical/legal issue in eliciting preferences from individuals. This work studies the problem of aggregating individual's voting data under the local differential privacy setting, where usefulness and soundness of the aggregated scores are of major concern. One naive approach to the problem is adding Laplace random noises, however, it makes aggregated scores extremely fragi...
1 Citations
May 7, 2019 in ICASSP (International Conference on Acoustics, Speech, and Signal Processing)
#1Bangzhou Xin (USTC: University of Science and Technology of China)H-Index: 1
#2Wei Yang (USTC: University of Science and Technology of China)H-Index: 15
Last. Liusheng Huang (USTC: University of Science and Technology of China)H-Index: 28
view all 4 authors...
As information security is increasingly valued, privacy-preserving data mining has become a research hotspot in the field of big data and signal processing. We propose a new differentially private greedy decision forest algorithm called DPGDF to help improve the accuracy of privacy-preserving data mining. Unlike previous algorithms that only employed greedy decision trees or random forests, our algorithm uses a combination of greedy trees and parallel combination theory to construct a greedy dec...
1 CitationsSource
12345678910