1 code implementation • 8 Apr 2018 • Linjie Deng, Yanxiang Gong, Yi Lin, Jingwen Shuai, Xiaoguang Tu, Yuefei Zhang, Zheng Ma, Mei Xie
Previous approaches for scene text detection usually rely on manually defined sliding windows.
Ranked #1 on Scene Text Detection on COCO-Text
1 code implementation • 17 Jan 2019 • Xiaoguang Tu, Jian Zhao, Mei Xie, Guodong Du, Hengsheng Zhang, Jianshu Li, Zheng Ma, Jiashi Feng
Face anti-spoofing (a. k. a presentation attack detection) has drawn growing attention due to the high-security demand in face authentication systems.
Ranked #2 on Face Anti-Spoofing on MSU-MFSD
no code implementations • 17 Jan 2019 • Xiaoguang Tu, Hengsheng Zhang, Mei Xie, Yao Luo, Yuefei Zhang, Zheng Ma
We propose a CNN framework using sparsely labeled data from the target domain to learn features that are invariant across domains for face anti-spoofing.
no code implementations • 17 Jan 2019 • Xiaoguang Tu, Hengsheng Zhang, Mei Xie, Yao Luo, Yuefei Zhang, Zheng Ma
Spatio-temporal information is very important to capture the discriminative cues between genuine and fake faces from video sequences.
1 code implementation • 21 Jan 2019 • Yanxiang Gong, Linjie Deng, Zheng Ma, Mei Xie
Recently, methods based on deep learning have dominated the field of text recognition.
2 code implementations • 22 Mar 2019 • Xiaoguang Tu, Jian Zhao, Zi-Hang Jiang, Yao Luo, Mei Xie, Yang Zhao, Linxiao He, Zheng Ma, Jiashi Feng
3D face reconstruction from a single 2D image is a challenging problem with broad applications.
Ranked #7 on Face Alignment on AFLW2000-3D
no code implementations • 16 May 2019 • Yao Luo, Xiaoguang Tu, Mei Xie
3D face reconstruction from a single 2D image is a very important topic in computer vision.
1 code implementation • 29 Aug 2019 • Linjie Deng, Yanxiang Gong, Xinchen Lu, Xin Yi, Zheng Ma, Mei Xie
Recently, scene text recognition methods based on deep learning have sprung up in computer vision area.
1 code implementation • 17 Sep 2019 • Linjie Deng, Yanxiang Gong, Xinchen Lu, Yi Lin, Zheng Ma, Mei Xie
To achieve high coverage of target boxes, a normal strategy of conventional one-stage anchor-based detectors is to utilize multiple priors at each spatial position, especially in scene text detection tasks.
no code implementations • 30 Dec 2019 • Hao Ge, Xiaoguang Tu, Mei Xie, Zheng Ma
We demonstrate that our two-stream architecture is robust to adversarial examples built by currently known attacking algorithms.
no code implementations • 3 Mar 2020 • Hao Ge, Xiaoguang Tu, Yanxiang Gong, Mei Xie, Zheng Ma
The interpretability of Convolutional Neural Networks (CNNs) is an important topic in the field of computer vision.
no code implementations • 21 May 2020 • Wenjie Ai, Xiaoguang Tu, Shilei Cheng, Mei Xie
Experiments results demonstrate that our RNAN achieves the comparable results with state-of-the-art methods in terms of both quantitative metrics and visual quality, however, with simplified network architecture.
no code implementations • 23 Mar 2021 • Shiyu Tang, Peijun Tang, Yanxiang Gong, Zheng Ma, Mei Xie
It draws class-wise features closer than coarse feature alignment or class-wise feature alignment only, therefore improves the model's performance to a great extent.
1 code implementation • 7 May 2022 • Yanxiang Gong, Linjie Deng, Shuai Tao, Xinchen Lu, Peicheng Wu, Zhiwei Xie, Zheng Ma, Mei Xie
With CRPD, a unified detection and recognition network with high efficiency is presented as the baseline.
no code implementations • 3 Dec 2022 • Yanxiang Gong, Zhiwei Xie, Guozhen Duan, Zheng Ma, Mei Xie
To address the issue, we propose a global distribution fitting (GDF) method with a penalty term to confine the generated data distribution.
no code implementations • 7 Mar 2024 • Yujiang Chen, Mei Xie
Recently, lung nodule detection methods based on deep learning have shown excellent performance in the medical image processing field.