no code implementations • 10 Oct 2023 • Min Ren, Muchan Tao, Xuecai Hu, Xiaotong Liu, Qiong Li, Yongzhen Huang
Gait is a complex form of motion, and hand-crafted gait features often only capture a fraction of the intricate associations between gait and depression risk.
1 code implementation • 27 Aug 2023 • Hongda Liu, Yunlong Wang, Min Ren, Junxing Hu, Zhengquan Luo, Guangqi Hou, Zhenan Sun
Secondly, we design a detached action-aware learning schedule to further mitigate the bias in the representation space.
1 code implementation • 27 Jul 2023 • Min Ren, Yunlong Wang, Yuhao Zhu, Kunbo Zhang, Zhenan Sun
Occlusion is a common problem with biometric recognition in the wild.
1 code implementation • 26 Jul 2022 • Xingqun Qi, Zhuojie Wu, Min Ren, Muyi Sun, Caifeng Shan, Zhenan Sun
Considering the domain-invariant representative vectors in MSAN, we propose two generalizable knowledge distillation schemes for cross-domain distillation, Dual Contrastive Graph Distillation (DCGD) and Domain-Invariant Cross Distillation (DICD).
1 code implementation • 13 Jul 2022 • Min Ren, Yuhao Zhu, Yunlong Wang, Zhenan Sun
A straightforward approach is to inactivate the adversarial perturbations so that they can be easily handled as general perturbations.
no code implementations • CVPR 2022 • Jianxin Sun, Qiyao Deng, Qi Li, Muyi Sun, Min Ren, Zhenan Sun
AnyFace can achieve high-quality, high-resolution, and high-diversity face synthesis and manipulation results without any constraints on the number and content of input captions.
no code implementations • 20 Oct 2021 • Jianze Wei, Huaibo Huang, Muyi Sun, Yunlong Wang, Min Ren, Ran He, Zhenan Sun
To make further efforts on accurate and reliable iris segmentation, we propose a bilateral self-attention module and design Bilateral Transformer (BiTrans) with hierarchical architecture by exploring spatial and visual relationships.
1 code implementation • ICCV 2021 • Min Ren, Lingxiao He, Xingyu Liao, Wu Liu, Yunlong Wang, Tieniu Tan
In this paper, we propose a novel Instance-level and Spatial-Temporal Disentangled Re-ID method (InSTD), to improve Re-ID accuracy.
Ranked #14 on Person Re-Identification on DukeMTMC-reID
1 code implementation • 1 Sep 2020 • Leyuan Wang, Kunbo Zhang, Min Ren, Yunlong Wang, Zhenan Sun
The quality metric proposed in this paper can significantly improve the performance of the recognition algorithm while reducing the number of images discarded for recognition, which is advantageous over hand-crafted factors based iris quality assessment methods.
2 code implementations • 1 Dec 2019 • Min Ren, Yunlong Wang, Zhenan Sun, Tieniu Tan
During dynamic graph matching, we propose a novel strategy to measure the distances of both nodes and adjacent matrixes.
no code implementations • 1 Dec 2019 • Min Ren, Caiyong Wang, Yunlong Wang, Zhenan Sun, Tieniu Tan
And illumination variations may cause irregular distortion of iris texture.
no code implementations • 26 Jul 2018 • Min Ren, Dabao Zhang
The construction stage consistently selects and estimates both common and differential effects by undertaking L1 regularized regression of each endogenous variable against the predicts of other endogenous variables as well as its anchoring exogenous variables.