About
Personal Blog of Zhangxuan Gu
2 Posts
Zhangxuan Gu
2 Posts
Zhangxuan Gu
AI Engineer in Ant Group
I am an Artificial Intelligence Researcher with Tiansuan Lab at Ant Group, which is under the leadership of Dr. Weiqiang Wang. My research benefits from collaboration with esteemed mentors and colleagues including Dr. Liqing Zhang, Dr. Li Niu, Scientist Haoxing Chen and Scientist Zhuoer Xu. I pursued my doctorate on Computer Science in Shanghai Jiao Tong University (SJTU), where I was mentored by Prof. Liqing Zhang and Prof. Li Niu. My B.E. was obtained also at SJTU for applied mathematics. My research interests include object detection, instance segmentation, image generation, self-supervised learning, computer vision, and machine learning. Currently, I focus on MLLM detection/grounding, AIGC.
  Post Charts
  My Curriculum Vitae

Education

  • Computer Vision Researcher
    Ant Group
    2022 - now
  • PhD in Computer Science
    Shanghai Jiao Tong University
    2016 - 2022
  • BSc in Mathematics
    Shanghai Jiao Tong University
    2012 - 2016

Publications

News !

  • [CVPR23] Gu, Zhangxuan & Zhuoer, Xu & Chen, Haoxing & Lan, Jun & Meng, Changhua & Wang, Weiqiang. (2023). Mobile User Interface Element Detection Via Adaptively Prompt Tuning. 11155-11164. 10.1109/CVPR52729.2023.01073.
  • [CVPR22] Gu, Zhangxuan & Meng, Changhua & Wang, Ke & Lan, Jun & Wang, Weiqiang & Gu, Ming & Zhang, Liqing. (2022). XYLayoutLM: Towards Layout-Aware Multimodal Networks For Visually-Rich Document Understanding. 4573-4582. 10.1109/CVPR52688.2022.00454.
  • [ICASSP24] [Oral] Gu, Zhangxuan & Chen, Haoxing & Zhuoer, Xu & Lan, Jun & Meng, Changhua & Wang, Weiqiang. (2022). DiffusionInst: Diffusion Model for Instance Segmentation. 10.48550/arXiv.2212.02773.
  • [ICME19] Gu, Zhangxuan & Zhang, Jianfu & Pan, Ziqi & Zhao, Haohua & Zhang, Liqing. (2019). Clothes Keypoints Localization and Attribute Recognition via Prior Knowledge. 550-555. 10.1109/ICME.2019.00101.
  • [ACMMM20] Gu, Zhangxuan & Zhou, Siyuan & Niu, Li & Zhao, Zihan & Zhang, Liqing. (2020). Context-aware Feature Generation For Zero-shot Semantic Segmentation. 1921-1929. 10.1145/3394171.3413593. Paper Code
  • [TMM] Gu, Zhangxuan & Niu, Li & Zhao, Haohua & Zhang, Liqing. (2020). Hard Pixel Mining for Depth Privileged Semantic Segmentation. IEEE Transactions on Multimedia. PP. 1-1. 10.1109/TMM.2020.3035231. Paper
  • [TNNLS] Gu, Zhangxuan & Zhou, Siyuan & Niu, Li & Zhao, Zihan & Zhang, Liqing. (2022). From Pixel to Patch: Synthesize Context-Aware Features for Zero-Shot Semantic Segmentation. IEEE Transactions on Neural Networks and Learning Systems. PP. 1-15. 10.1109/TNNLS.2022.3145962. Paper Code
  • [ACMMM23] Chen, Haoxing & Gu, Zhangxuan & Li, Yaohui & Lan, Jun & Meng, Changhua & Wang, Weiqiang & Li, Huaxiong. (2023). Hierarchical Dynamic Image Harmonization. 1422-1430. 10.1145/3581783.3611747.
  • [ICCV23] Zhuoer, Xu & Gu, Zhangxuan & Zhang, Jianping & Cui, Shiwen & Meng, Changhua & Wang, Weiqiang. (2023). Backpropagation Path Search On Adversarial Transferability. 4640-4650. 10.1109/ICCV51070.2023.00430.

Contact