Dongze Lian

  final-year Ph.D. Student

  School of Information Science and Technology

  ShanghaiTech University

  Email: liandz [at] shanghaitech [dot] edu [dot] cn


Biography

I am a final-year Ph.D. student of School of Information Science and Technology at ShanghaiTech University, advised by Prof. Shenghua Gao at ShanghaiTech Vision and Intelligent Perception Lab (SVIP Lab). I have also the opportunity to work with Dr. Yin Zheng and Dr. Peilin Zhao in Tencent AI Lab. My research focuses on computer vision (e.g., gaze estimation, crowd counting, object detection) and deep learning (e.g., explanation, design and search of deep neural network. Before joining ShanghaiTech University, I received my Bachelor's Degree in Dalian University of Technology (DUT).

[Google Scholar] [LinkedIn] [DBLP]


News
  • 2021/10 -- Two papers are accepted by TPAMI.
  • 2021/07 -- One paper is accepted by ICCV 2021.
  • 2021/06 -- Got my PhD degree. Congrats to myself - Dr. Lian!
  • 2021/03 -- One paper is accepted by CVPR 2021.
  • 2020/12 -- One paper is accepted by AAAI 2021.
  • 2020/04 -- We achieved the 3rd Place of DeepFashion2 Challenge – Landmark Estimation Track (CVPR 2020 Workshop).
  • 2019/12 -- One paper is accepted by ICLR 2020.
  • 2019/08 -- One paper is accepted by TPAMI.
  • 2019/02 -- Three papers are accepted by CVPR 2019.
  • 2018/12 -- I worked as a research intern in Tencent AI Lab.
  • 2018/11 -- One paper is accepted by AAAI 2019.
  • 2018/09 -- One paper is accepted by ACCV 2018 (Oral).
  • 2018/07 -- One paper is accepted by TNNLS.
  • 2018/07 -- One paper is accepted by ECCV 2018.
  • 2018/03 -- One paper is accepted by CVPR 2018.

Publications
Conference
  • AS-MLP: An Axial Shifted MLP Architecture for Vision
    Dongze Lian*, Zehao Yu*, Xing Sun, Shenghua Gao
    arXiv:2107.08391, 2021.
    [Paper] [Code]
  • Look Before You Leap: Learning Landmark Features for One-Stage Visual Grounding
    Binbin Huang, Dongze Lian, Weixin Luo, Shenghua Gao
    IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), 2021.
    [Paper] [Code]
  • KGDet: Keypoint-Guided Fashion Detection
    Shenhan Qian*, Dongze Lian*, Binqiang Zhao, Tong Liu, Bohui Zhu, Hai Li, Shenghua Gao
    AAAI Conference on Artificial Intelligence (AAAI), 2021.
    [Paper] [Code]
  • Towards Fast Adaptation of Neural Architectures with Meta Learning
    Dongze Lian*, Yin Zheng*, Yintao Xu, Yanxiong Lu, Leyu Lin, Peilin Zhao, Junzhou Huang, Shenghua Gao
    International Conference on Learning Representations (ICLR), 2020.
    [Paper] [Code]
  • Density Map Regression Guided Detection Network for RGB-D Crowd Counting and Localization
    Dongze Lian*, Jing Li*, Jia Zheng, Weixin Luo, Shenghua Gao
    IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), 2019.
    [Paper] [Code]
  • Local to Global Learning: Gradually Adding Classes for Training Deep Neural Networks
    Hao Cheng*, Dongze Lian*, Bowen Deng, Shenghua Gao, Tao Tan, Yanlin Geng
    IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), 2019.
    [Paper] [Code]
  • Single-Image Piece-wise Planar 3D Reconstruction via Associative Embedding
    Zehao Yu*, Jia Zheng*, Dongze Lian, Zihan Zhou, Shenghua Gao
    IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), 2019.
    [Paper] [Code]
  • RGBD Based Gaze Estimation via Multi-task CNNs
    Dongze Lian*, Ziheng Zhang*, Weixin Luo, Lina Hu, Minye Wu, Zechao Li, Jingyi Yu, Shenghua Gao
    AAAI Conference on Artificial Intelligence (AAAI), 2019.
    [Paper] [Code]
  • Evaluating Capability of Deep Neural Networks for Image Classification via Mutual Information
    Hao Cheng, Dongze Lian, Shenghua Gao, Yanlin Geng
    European Conference on Computer Vision (ECCV), 2018.
    [Paper]
  • Believe It or Not, We Know What You Are Looking at!
    Dongze Lian*, Zehao Yu*, Shenghua Gao
    Asian Conference on Computer Vision (ACCV Oral, 4.6%), 2018.
    [Paper] [Code]
  • Future Frame Prediction for Anomaly Detection – A New Baseline
    Wen Liu*, Weixin Luo*, Dongze Lian, Shenghua Gao
    IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), 2018.
    [Paper] [Code]
Journal
  • Video Anomaly Detection with Sparse Coding Inspired Deep Neural Networks
    Weixin Luo*, Wen Liu*, Dongze Lian, Jinhui Tang, Lixin Duan, Xi Peng, Shenghua Gao
    IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2019.
    [Paper] [Code]
  • Utilizing Information Bottleneck to Evaluate the Capability of Deep Neural Networks for Image Classification
    Hao Cheng, Dongze Lian, Shenghua Gao, Yanlin Geng
    Entropy, 2019.
    [Paper]
  • Multi-view Multi-task Gaze Prediction with Deep Convolutional Neural Networks
    Dongze Lian, Lina Hu, Weixin Luo, Yanyu Xu, Lixin Duan, Jingyi Yu, Shenghua Gao
    IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2018.
    [Paper] [Code]

Professional Service
  • Journal Reviewer:
    IEEE Transactions on Neural Networks and Learning Systems (TNNLS)
    IEEE Transactions on Circuits and Systems for Video Technology (TCSVT)
    Neurocomputing
  • Conference Reviewer:
    CVPR (2020-2022), ICCV (2019-2021), ECCV (2020), NeurIPS (2020-2021), ICLR (2022), AAAI (2020-2021), WACV (2021-2022), ACCV (2020)
  • Student Volunteer:
    AAAI (2021), RACV (2016)

Teaching
  • Teaching Assistant -- Computer Vision II at ShanghaiTech University, Spring 2020
  • Teaching Assistant -- Computer Vision I at ShanghaiTech University, Fall 2019
  • Teaching Assistant -- Computer Vision II at ShanghaiTech University, Spring 2018
  • Teaching Assistant -- Computer Vision I at ShanghaiTech University, Fall 2017

Awards
  • Outstanding Doctoral Graduates of Shanghai, 2021
  • Outstanding Doctoral Graduates of ShanghaiTech University, 2021
  • National Scholarship for Doctoral Students 2020
  • Outstanding Student of ShanghaiTech University, 2019 - 2020
  • Outstanding Student of ShanghaiTech University, 2018 - 2019
  • Outstanding Graduates of Dalian University of Technology, 2016


© Dongze Lian | Last updated: Oct, 2021