no code implementations • 12 Jun 2022 • Wen Su, Qingna Li
By exploring the special property of nonlinear SVMs, we transform the optimization problem of attacking nonlinear SVMs into a nonlinear KKT system.
no code implementations • 15 Apr 2022 • Jiwei Chen, Kewei Wang, Wen Su, Zengfu Wang
Existing methods with simple Euclidean distance algorithm indiscriminately optimize the hard and easy examples so that the densities of hard examples are usually incorrectly predicted to be lower or even zero, which results in large counting errors.
no code implementations • 15 Apr 2022 • Jiwei Chen, Wen Su, Zengfu Wang
Crowd counting is a challenging problem due to the scene complexity and scale variation.
no code implementations • 7 Apr 2022 • Wen Su, Qingna Li, Chunfeng Cui
In this paper, we investigate the optimization models and the interpretations for three types of adversarial perturbations against support vector machines, including sample-adversarial perturbations (sAP), class-universal adversarial perturbations (cuAP) as well as universal adversarial perturbations (uAP).
no code implementations • 21 Jul 2021 • Wen Su
This paper focus on pricing exchange option based on copulas by MCMC algorithm.
no code implementations • 21 Jul 2021 • Wen Su
This paper presents a new method to assess default risk based on applying the CEV process to the KMV model.
no code implementations • 20 Jul 2021 • Wen Su
The rolling estimation window is recommended when using the historical volatility.
8 code implementations • 24 Nov 2019 • Jia Li, Wen Su, Zengfu Wang
We rethink a well-know bottom-up approach for multi-person pose estimation and propose an improved one.
Ranked #9 on Keypoint Detection on COCO test-dev
no code implementations • 27 May 2019 • Hao Wang, Tong Xu, Qi Liu, Defu Lian, Enhong Chen, Dongfang Du, Han Wu, Wen Su
Recently, the Network Representation Learning (NRL) techniques, which represent graph structure via low-dimension vectors to support social-oriented application, have attracted wide attention.