Dongchao Wen (温东超)

alt text 


Research Fellow

Inspur Electronic Information Industry Co., Ltd (浪潮电子信息产业股份有限公司), Beijing China.

Professor of Engineering (正高级工程师)
Chinese Academy of Sciences

Review Committee Member for Engineering and Technical Titles of the Chinese Academy of Sciences
Review Committee Member for Engineering and Technical Titles of Shandong Province

https://dblp.org
https://ieeexplore.org
https://www.semanticscholar.org

Education & Qualification

I received the B.E. degree (Prof. Jingwen Li （李景文）) in electronic information engineering and the M.S. degree (under supervision of Prof. Yinqing Zhou （周荫清） and Prof. Jie Chen （陈杰）) in signal and information processing from Beihang University, Beijing, China, in 2002 and 2005, respectively. After that, I got a professor's qualification certificate (professor of engineering) of Chinese Academy of Sciences in 2018.

Research Interest

My current research interests are: 1) Trustworthy AI (Robustness & Reliability, Explainability, Security & Privacy, etc.) and 2) Human Analysis (e.g. face detection/tracking/recognition, etc.).

Professional Experience

I joined Inspur Electronic Information Industry Co., Ltd in 2021.05.

Between April 2006 and May 2021 , I was a Senior Research Scientist at Canon Information Technology (Beijing) Co., Ltd. (also as Canon Innovative Solution (Beijing) Co., Ltd.), leading a young and creative group of about 10 people focusing on forward-looking research works on deep learning, e.g. network architecture design, model compression (e.g. low-bits CNN), stochastic optimization methods, AutoML(e.g. NAS), etc.

In 2019 and 2020, I was as Principal Investigator of face recognition technology collaborating with Beijing University of Posts and Telecommunications to participate NIST FRVT contest.

Patents

I have already filed 80+ patents in CN, JP and US.

News

  • Face Recognition: My team achieved Rank No.5@(Investigation (R=1, T=0)by Developer) (total: 116 entries) in the world in NIST FRVT 1:N contest On July.5th, 2023. (Team name: CompanyName-000, 1st submission)

    • NIST FRVT

  • Face Recognition: My team achieved Rank No.5@wild category (total: 493 entries) in the world in NIST FRVT 1:1 contest On March.9th, 2023. (Team name: CompanyName-001, 2nd submission)

    • NIST FRVT

Achievements in Canon

  • Face Recognition: My team achieved Rank No.2@Visa-Border, No.1@Visa-Kiosk in the world in NIST FRVT 1:N Investigation contest On Nov.5th, 2020. (Team name: cib-000, 1st submission)

  • Face Recognition: My team achieved Rank No.8 in the world in NIST FRVT 1:N Identification contest On Nov.5th, 2020. (Team name: cib-000, 1st submission)

  • Face Recognition: My team achieved Rank No.5 in the world in NIST FRVT 1:1 contest On Jan.19th, 2021. (Team name: canon-002, 3rd submission)

  • Face Recognition: My team achieved Rank No.4 in the world in NIST FRVT 1:1 contest On Aug.5th, 2020. (Team name: cib-001, 2nd submission)

  • Face Recognition: My team achieved Rank No.25 in the world in NIST FRVT 1:1 contest On Dec.12th, 2019.(Team name: cib-000, 1st submission)

    • NIST FRVT

Publications

In 2024

  • Confidence-Aware RGB-D Face Recognition via Virtual Depth Synthesis
    Zijian Chen, Mei Wang, Weihong Deng, Hongzhi Shi, Dongchao Wen *, Yingjie Zhang, Xingchen Cui, Jian Zhao.
    IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) 2024.

  • Enhancing Generalization of Invisible Facial Privacy Cloak via Gradient Accumulation
    Xuannan Liu, Yaoyao Zhong, Weihong Deng, Hongzhi Shi, Xingchen Cui, Yunfeng Yin, Dongchao Wen *.
    IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2024.

In 2023

  • Gradient Attention Balance Network: Mitigating Face Recognition Racial Bias via Gradient Attention 【Paper】
    Linzhi Huang, Mei Wang, Jiahao Liang, Weihong Deng, Hongzhi Shi, Dongchao Wen *, Yingjie Zhang, Jian Zhao.
    IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) 2023. (Oral)

  • Dive into the Resolution Augmentations and Metrics in Low Resolution Face Recognition: A Plain yet Effective New Baseline【Paper】
    Xu Ling, Yichen Lu, Wenqi Xu, Weihong Deng, Yingjie Zhang, Xingchen Cui, Hongzhi Shi, Dongchao Wen *.
    R2HCAI: The AAAI 2023 Workshop on Representation Learning for Responsible Human-Centric AI at AAAI Conference on Artificial Intelligence 2023 (AAAI) 2023.

  • Model and Data Agreement for Learning with Noisy Labels【Paper】
    Yuhang Zhang, Weihong Deng, Xingchen Cui, Yunfeng Yin, Hongzhi Shi, Dongchao Wen *.
    2nd International Workshop on Practical Deep Learning in the Wild Workshop at AAAI Conference on Artificial Intelligence 2023 (AAAI) 2023.

In 2022

  • Face Clustering via Adaptive Aggregation of Clean Neighbors.【Paper】
    Shiyong Hong, Yaobin Zhang, Xu Ling, Weihong Deng, Yin Yunfeng, Zhang Yingjie, Hongzhi Shi, Dongchao Wen *.
    The 3rd International Workshop on Human-Centric Multimedia Analysis (HCMA '22) in conjunction with ACM International Conference on Multimedia (MM) 2022.

  • Improving Autism Spectrum Disorder Prediction by Fusion of Multiple Measures of Resting-State Functional MRI Data.【Paper】
    Lingyan Liang, Gang Dong, Changsheng Li, Dongchao Wen , Yaqian Zhao, Jing Li.
    44th Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC)2022. (Oral)

  • Dynamic Training Data Dropout for Robust Deep Face Recognition.【Paper】
    Yaoyao Zhong, Weihong Deng,Han Fang, Jiani Hu, Dongyue Zhao, Xian Li, Dongchao Wen .
    IEEE Transactions on Multimedia (TMM) 2022.

In 2021

  • FTAFace: Context-enhanced Face Detector with Fine-grained Task Attention.【Paper】
    Deyu Wang, Dongchao Wen *, Wei Tao, Lingxiao Yin, Tse-Wei Chen, Tadayuki Ito, Kinya Osa, Masami Kato.
    ACM International Conference on Multimedia (MM) 2021.

  • CASSOD-Net: Cascaded and Separable Structures of Dilated Convolutional Neural Networks for Embedded Vision Systems and Applications.【Paper】
    Tse-Wei Chen, Deyu Wang, Wei Tao,Dongchao Wen, Lingxiao Yin, Tadayuki Ito, Kinya Osa, Masami Kato.
    IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) 2021. (Oral)

  • Augmented Face Representation Learning via Transitive Distillation.【Paper】
    Han Fang, Weihong Deng, Yaoyao Zhong, Jiani Hu, Dongyue Zhao, Xian Li, Dongchao Wen .
    IEEE International Conference on Automatic Face and Gesture Recognition 2021 (FG) 2021.

  • Adaptive Label Noise Cleaning with Meta-Supervision for Deep Face Recognition.【Paper】
    Yaobing Zhang, Weihong Deng, Yaoyao Zhong, Jiani Hu, Xian Li, Dongyue Zhao, Dongchao Wen .
    International Conference on Computer Vision (ICCV) 2021.

  • Sigmoid-constrained Hyper-sphere Loss for Robust Face Recognition. 【Paper】
    Yaoyao Zhong, Weihong Deng, Jiani Hu, Dongyue Zhao, Xian Li, Dongchao Wen .
    IEEE Transactions on Image Processing(TIP), 2021.
    开源：基于 SFace 损失函数训练的轻量人脸识别模型贡献了 OpenCV开源库（全球最受欢迎的计算机视觉开源软件，Github 五万多星）的人脸识别模块（附实例程序）

In 2020

  • Fully Supervised and Guided Distillation for One-Stage Detectors.【Paper】
    Deyu Wang, Dongchao Wen *, Junjie Liu, Wei Tao, Tse-Wei Chen, Kinya Osa, Masami Kato.
    Asian Conference on Computer Vision (ACCV) 2020.

  • QuantNet: Learning to Quantize by Learning within Fully Differentiable Framework.【Paper】
    Junjie Liu, Dongchao Wen *, Deyu Wang, Wei Tao, Tse-Wei Chen, Kinya Osa, Masami Kato.
    European Conference on Computer Vision Workshops (ECCVW) 2020. (Oral)

  • Hardware Architecture of Embedded Inference Accelerator and Analysis of Algorithms for Depthwise and Large-Kernel Convolutions.【Paper】
    Tse-Wei Chen, Wei Tao, Deyu Wang, Dongchao Wen, Masami Kato, Kinya Osa.
    European Conference on Computer Vision Workshops (ECCVW) 2020. (Oral)

  • BAMSProd: A Step towards Generalizing the Adaptive Optimization Methods to Deep Binary Model.【Paper】
    Junjie Liu, Dongchao Wen, Deyu Wang, Wei Tao, Tse-Wei Chen, Kinya Osa, Masami Kato.
    IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) 2020. (Oral)

  • Global-Local GCN: Large-Scale Label Noise Cleansing for Face Recognition.【Paper】
    Yaobing Zhang, Weihong Deng, Mei Wang, Jiani Hu, Xian Li, Dongyue Zhao, Dongchao Wen .
    IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2020.

In 2019

  • Condensation-Net: Memory-Efficient Network Architecture With Cross-Channel Pooling Layers and Virtual Feature Maps.【Paper】
    Tse-Wei Chen, Motoki Yoshinaga, Hongxing Gao, Wei Tao, Dongchao Wen, Junjie Liu, Kinya Osa, Masami Kato.
    IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) 2019.

  • DupNet: Towards Very Tiny Quantized CNN With Improved Accuracy for Face Detection.【Paper】
    Hongxing Gao, Wei Tao, Dongchao Wen, Junjie Liu, Tse-Wei Chen, Kinya Osa, Masami Kato.
    IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) 2019.

  • Knowledge Representing: Efficient, Sparse Representation of Prior Knowledge for Knowledge Distillation.【Paper】
    Junjie Liu, Dongchao Wen, Hongxing Gao, Wei Tao, Tse-Wei Chen, Kinya Osa, Masami Kato.
    IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) 2019.

In 2018

  • IFQ-Net: Integrated Fixed-Point Quantization Networks for Embedded Vision.【Paper】
    Hongxing Gao, Wei Tao, Dongchao Wen, Tse-Wei Chen, Kinya Osa, Masami Kato.
    IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) 2018. (Oral)

Patents

Granted US Patents

  • US11847569B2, Training and application method of a multi-layer neural network model, apparatus and storage medium，Tao Wei，Gao Hongxing，Chen Tsewei，Wen Dongchao，Liu Junjie.

  • US11755880B2, Method and apparatus for optimizing and applying multilayer neural network model, and storage medium，Gao Hongxing，Tao Wei，Chen Tsewei，Wen Dongchao.

  • US11270108B2, Object tracking method and apparatus, Wang Shiting, Hu Qi, Wen Dongchao.

  • US11106945B2, Training and application method of neural network model, apparatus, system and storage medium, Liu Junjie, Chen Tsewei, Wen Dongchao, Gao Hongxing, Tao Wei.

  • US10475204B2, Fast multi-object detection and tracking system, Wang Shiting, Hu Qi, Wen Dongchao.

  • US10318797B2, Image processing apparatus and image processing method, Sun Donghui, Li Xian, Wen Dongchao.

  • US9600884B2, Object shape aligning apparatus, object processing apparatus and methods thereof, Zhu Fuguo, Jiang Yong, Li Xian, Xu Lifeng, Wen Dongchao.

Activities

  • The Embedded Vision Workshop (in conjunction with CVPR Since 2005)
    • alt text 

    Program Committee member
    2018/2019/2020/2021/2022/2023

    The Embedded Vision Workshop

Professional Services

Projects

  • ---

Honors and Awards

    Inspur Electronic Information Industry Co., Ltd

  • Outstanding Staff of the Year 2023 (Crystal Award), Inspur Electronic Information Industry Co., Ltd., January 2024

  • Outstanding Paper Award for 2022 (Top-3), Inspur Electronic Information Industry Co., Ltd., April 2023

  • Outstanding Staf of the Year 2022 (Crystal Award), Inspur Electronic Information Industry Co., Ltd., January 2023

  • Best New Employee Award of the Year 2021, Inspur Electronic Information Industry Co., Ltd., April 2022

    • 佳能信息技术(北京)有限公司

  • 科技创新英才, 中关村科学城总工会, 2021 年 4 月

  • 2020年度优秀技术成果奖, 佳能信息技术(北京)有限公司, 2021 年 1 月

  • 2019年度优秀专利提案奖, 佳能集团, 2020 年 7 月

  • 2019年度优秀技术成果奖, 佳能信息技术(北京)有限公司, 2020 年 1 月

  • 2018年A 级专利奖, 佳能信息技术(北京)有限公司, 2019 年 1 月

  • 2018年优秀专利团队奖, 佳能信息技术(北京)有限公司, 2019 年 1 月

  • 2017年优秀专利团队奖, 佳能信息技术(北京)有限公司, 2018 年 1 月

  • 2015年优秀专利团队奖, 佳能信息技术(北京)有限公司, 2016 年 1 月

  • 2007年优秀员工, 佳能信息技术(北京)有限公司, 2008 年 1 月

  • 2007年A 级专利奖, 佳能信息技术(北京)有限公司, 2008 年 1 月

    大学阶段

  • 611奖学金, 颁发机构 北京航空航天大学,获奖日期 2004 年

  • 光华奖学金, 颁发机构 北京航空航天大学,获奖日期 2003 年

  • 人民奖学金, 颁发机构 北京航空航天大学,获奖日期 1999 年

    高中阶段

  • 内蒙古自治区三好学生, 获奖日期 1997 年

  • 内蒙古自治区三好学生, 获奖日期 1996 年

Other Services

  • 佳能信息技术(北京)有限公司 员工代表委员会主任/工会主席 2008年--2020年

  • 佳能信息技术(北京)有限公司 党支部书记 2007年--2019年

  • 北京航空航天大学 电子信息工程学院 研究生会主席, 2003年--2004年

Welcome Visitors