DEYI
≡

Deyi Ji

I am a senior research scientist at Alibaba DAMO Academy and Alibaba Cloud, where I work with Prof. Jieping Ye and Prof. Xian-Sheng Hua on deep learning, computer vision and machine learning.

I have been also studying for a Ph.D degree at University of Science and Technology of China since 2022, by the “Doctoral Program for Future Technology Leading Talents in National Key Fields”, co-advised by Prof. Feng Zhao and Prof. Feng Wu.

Before that, I worked as a research scientist at SenseTime with Dr. Wei Wu and Dr. Junjie Yan, in Prof. Xiaogang Wang's team.

I received my Master's degree of Computer Science in Shanghai Jiao Tong University at 2019, where I was advised by Prof. Hongtao Lu, and Bachelor's degree in Huazhong University of Science and Technology at 2016, co-advised by Prof. Yu Liu and Prof. Xinggang Wang.

Email : jideyi16@foxmail.com  /  Google Scholar

News

  • 06/2024, Our works about the applications of xLSTM and Segment Anything V2 are released.

  • 05/2024, 1 paper has been submitted to NeurIPS 2024.

  • 05/2024, 1 paper has been accepted by ICML 2024 (Spotlight, 2% of submitted papers, 7% of accepted papers).

  • 02/2024, 1 paper has been accepted by CVPR 2024.

  • 04/2023, 1 journal paper has been submitted to TPAMI.

  • 04/2023, 1 paper has been accepted by IJCAI 2023.

  • 03/2023, 1 paper has been accepted by CVPR 2023.

  • 03/2022, 1 paper has been accepted by CVPR 2022.

  • 07/2021, 1 journal paper has been accepted by TNNLS 2021.

  • 07/2021, 1 journal paper has been accepted by TIP 2021.

  • 03/2021, 1 paper has been accepted by CVPR 2021.

  • 12/2020, 1 paper has been accepted by AAAI 2021.

  • 07/2020, 1 paper has been accepted by ECCV 2020.

  • 04/2018, Second Place at NVDIA AI CITY Challenge and 1 paper has been accepted CVPR 2018 Workshop Oral.

    • Research

    I'm interested in Large Vision-Language Models, Scene Understanding, Semantic Segmentation, Target Re-identification, Knowledge Distillation, etc. (^ students mentored by me.)

    Conference Papers:

    1. Discrete Latent Perspective Learning for Segmentation and Detection
      Deyi Ji, Feng Zhao, Lanyun Zhu, Wenwei Jin, Hongtao Lu, Jieping Ye
      ICML 2024 (Spotlight, 2% of submitted papers, 7% of accepted papers)

    2. Llafs: When Large-Language Models Meet Few-Shot Segmentation
      Lanyun Zhu^, Tianrun Chen, Deyi Ji, Jieping Ye, Jun Liu
      CVPR 2024

    3. Guided Patch-Grouping Wavelet Transformer with Spatial Congruence for Ultra-High Resolution Segmentation
      Deyi Ji, Feng Zhao, Hongtao Lu
      IJCAI 2023

    4. Ultra-High Resolution Segmentation with Ultra-Rich Context: A Novel Benchmark
      Deyi Ji, Feng Zhao, Hongtao Lu, Mingyuan Tao, Jieping Ye
      CVPR 2023

    5. Structural and Statistical Texture Knowledge Distillation for Semantic Segmentation
      Deyi Ji, Haoran Wang, Mingyuan Tao, Jianqiang Huang, Xian-Sheng Hua, Hongtao Lu
      CVPR 2022

    6. Learning Statistical Texture for Semantic Segmentation
      Lanyu Zhu*^, Deyi Ji*, Shiping Zhu, Weihao Gan, Wei Wu, Junjie Yan
      CVPR 2021 (Equal Contribution) | paper | code

    7. Context-Aware Graph Convolution Network for Target Re-identification
      Deyi Ji, Haoran Wang, Hanzhe Hu, Weihao Gan, Wei Wu, Junjie Yan
      AAAI 2021 | paper

    8. Class-wise dynamic graph convolution for semantic segmentation
      Hanzhe Hu^, Deyi Ji, Weihao Gan, Shuai Bai, Wei Wu, Junjie Yan
      ECCV 2020 | paper

    9. Challenges on large scale surveillance video analysis
      Weitao Feng, Deyi Ji, Yiru Wang, Shuorong Chang, Hansheng Ren, Weihao Gan
      CVPR Workshop 2018 | paper | Oral Presentation

    Journal Papers:

    1. Learning Social Spatio-Temporal Relation Graph in the Wild and a Video Benchmark
      Haoran Wang^, Licheng Jiao, Fang Liu, Lingling Li, Xu Liu, Deyi Ji, Weihao Gan
      IEEE TIP 2021

    2. IPGN: Interactiveness Proposal Graph Network for Human-Object Interaction Detection
      Haoran Wang^, Licheng Jiao, Fang Liu, Lingling Li, Xu Liu, Deyi Ji, Weihao Gan
      IEEE TNNLS 2021

    Services

  • Conference Reviewer: ICML, NeurIPS, ICLR, CVPR, ICCV, ECCV, AAAI, IJCAI.

  • Journal Reviewer: IEEE TPAMI, IJCV.

    • Thanks for this website's source code
    No. Visitor Since Feb 2022. Powered by w3.css