avatar

Quan Tang (唐泉)

Senior Research Scientist
Pengcheng Laboratory
tangq (at) pcl.ac.cn

Great research rarely flourishes under constant pressure. When you feel weary, step away without guilt. Take a walk, clear your mind, and return when curiosity feels alive again.

About Me

I am a Senior Research Scientist at Pengcheng Laboratory, Shenzhen, China. My current work focuses on bringing advanced computer vision and embodied intelligence technologies into real-world industrial systems.

I obtained my B.Sc. and Ph.D. degrees in Computer Science from South China University of Technology in 2018 and 2024, respectively. I pursued my doctoral research under the supervision of Prof. Fagui Liu and worked closely with Prof. Tong Zhang and Prof. C. L. Philip Chen. During my Ph.D. studies, I visited the Australian Institute for Machine Learning at the University of Adelaide in 2022 and the Computer Vision Lab at ETH Zürich in 2023. I also interned at Huawei Noah’s Ark Lab, where I worked with Dr. Chuanjian Liu and Dr. Kai Han.

My research lies at the intersection of Computer Vision and Deep Learning, with the goal of building Agentic Visual Intelligence. Within this broader vision, I focus on dynamic scene understanding, multimodal learning, efficient models, industrial visual inspection, and 3D scene generation and reconstruction. I also bring complementary expertise in data stream classification and anomaly detection.

Prospective Students

I am always happy to work with self-motivated students who are interested in computer vision. If you would like to explore research opportunities with me, please feel free to email me with your CV and a short research statement.

Applications are now open for Ph.D. positions starting in Fall 2027 through the joint doctoral program between Pengcheng Laboratory and Sun Yat-sen University. Students will be co-supervised by me and either Prof. Jiemin Xie or Prof. Chao Gou.

News

Selected Publications

  1. ECCV
    ModuSeg: Decoupling Object Discovery and Semantic Retrieval for Training-Free Weakly Supervised Segmentation
    Qingze He, Fagui Liu*, Dengke Zhang, Qingmao Wei, Quan Tang* (*Corresponding authors)
    European Conference on Computer Vision (ECCV), 2026.
    PDF Code Poster Presentation

  2. ECCV
    Motion-aware Sparse Pipeline for Lightweight Object Tracking
    Qingmao Wei, Fagui Liu*, Dengke Zhang, Qingze He, Quan Tang* (*Corresponding authors)
    European Conference on Computer Vision (ECCV), 2026.
    PDF Code Poster Presentation

  3. SPL
    CaSS: Category-Aware Semantic Segmentation with Vision–Language Priors
    Quan Tang, Dengke Zhang, Xuhao Tang, Bin Wang, Cuifeng Du, Jun Jiang* (*Corresponding author)
    IEEE Signal Processing Letters (IEEE SPL), 2026.
    PDF Code

  4. TIP
    Rethinking Feature Reconstruction via Category Prototype in Semantic Segmentation
    Quan Tang, Chuanjian Liu, Fagui Liu*, Jun Jiang, Bowen Zhang, C. L. Philip Chen, Kai Han, Yunhe Wang* (*Corresponding authors)
    IEEE Trasactions on Image Processing (TIP), 2025.
    PDF Code

  5. ICCV
    CorrCLIP: Reconstructing Patch Correlations in CLIP for Open-Vocabulary Semantic Segmentation
    Dengke Zhang, Fagui Liu*, Quan Tang* (*Corresponding authors)
    IEEE/CVF International Conference on Computer Vision (ICCV), 2025.
    PDF Code Oral Presentation

  6. IMAVIS
    Increase the Sensitivity of Moderate Examples for Semantic Image Segmentation
    Quan Tang, Fagui Liu*, Dengke Zhang, Jun Jiang, Xuhao Tang, C. L. Philip Chen (*Corresponding author)
    Image and Vision Computing (IMAVIS), 2025.
    PDF Code

  7. SPL
    Exploring Token-Level Augmentation in Vision Transformer for Semi-Supervised Semantic Segmentation
    Dengke Zhang, Quan Tang*, Fagui Liu*, Haiqing Mei, C. L. Philip Chen (*Corresponding authors)
    IEEE Signal Processing Letters (IEEE SPL), 2025.
    PDF Code

  8. ICASSP
    EK-Net:Real-time Scene Text Detection with Expand Kernel Distance
    Boyuan Zhu, Fagui Liu*, Xi Chen, Quan Tang* (*Corresponding authors)
    IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2024.
    PDF Oral Presentation

  9. ICCV
    Dynamic Token Pruning in Plain Vision Transformers for Semantic Segmentation
    Quan Tang†, Bowen Zhang†, Jiajun Liu, Fagui Liu*, Yifan Liu* (†Equal Contribution, *Corresponding authors)
    IEEE/CVF International Conference on Computer Vision (ICCV), 2023.
    PDF Code Poster Presentation

  10. ICCV
    Boosting Semantic Segmentation from the Perspective of Explicit Class Embeddings
    Yuhe Liu, Chuanjian Liu, Kai Han*, Quan Tang, Zengchang Qin* (*Corresponding authors)
    IEEE/CVF International Conference on Computer Vision (ICCV), 2023.
    PDF Code Poster Presentation

  11. TITS
    Compensating for Local Ambiguity with Encoder-Decoder in Urban Scene Segmentation
    Quan Tang, Fagui Liu*, Tong Zhang, Jun Jiang, Yu Zhang, Boyuan Zhu, Xuhao Tang (*Corresponding author)
    IEEE Transactions on Intelligent Transportation Systems (TITS), 2022.
    PDF Code

  12. TITS
    EPRNet: Efficient Pyramid Representation Network for Real-Time Street Scene Segmentation
    Quan Tang, Fagui Liu*, Jun Jiang, Yu Zhang (*Corresponding author)
    IEEE Transactions on Intelligent Transportation Systems (TITS), 2022.
    PDF Code

  13. arXiv
    Category Feature Transformer for Semantic Segmentation
    Quan Tang, Chuanjian Liu, Fagui Liu, Yifan Liu, Jun Jiang, Bowen Zhang, Kai Han, Yunhe Wang
    arXiv, 2022.
    PDF Code

  14. NeurIPS
    SegViT: Semantic Segmentation with Plain Vision Transformers
    Bowen Zhang†, Zhi Tian†, Quan Tang, Xiangxiang Chu, Xiaolin Wei, Chunhua Shen*, Yifan Liu (†Equal Contribution, *Corresponding authors)
    Conference on Neural Information Processing Systems (NeurIPS), 2022.
    PDF Code Poster Presentation

  15. IMAVIS
    Attention-guided Chained Context Aggregation for Semantic Segmentation
    Quan Tang, Fagui Liu*, Tong Zhang, Jun Jiang, Yu Zhang (*Corresponding author)
    Image and Vision Computing (IMAVIS), 2021.
    PDF Code

Note: For a complete list of publications, please see my Google Scholar profile.

Academic Services

Conference Reviewer

Journal Reviewer

Awards

The Group

Overview

The Agentic Visual Intelligence Group (AVIG) explores visual intelligence that can understand, reason about, and interact with complex real-world environments.

Agentic Visual Intelligence

Visual agents capable of perceiving, reasoning, and adapting in complex real-world environments.

Vision Understanding

Dynamic scene parsing, multimodal representation learning, 3D scene generation and reconstruction.

Edge Intelligence

Efficient models, knowledge distillation, and resource-aware learning for on-device visual perception.

Students

Qingmao Wei

Qingmao Wei

Ph.D. Student

w/ Prof. Fagui Liu

Since Fall 2024

Zhiwen Ji

Zhiwen Ji

Ph.D. Student

w/ Prof. Xiangwei Zhu

Since Fall 2025

Dengke Zhang

Dengke Zhang

Ph.D. Student

w/ Prof. Fagui Liu

Since Fall 2024

Qingze He

Qingze He

Ph.D. Student

w/ Prof. Fagui Liu

Since Spring 2026

Jiulin Qin

Jiulin Qin

Master’s Student

w/ Prof. Fagui Liu

Since Fall 2025

Chufeng Duan

Chufeng Duan

Collaborating Ph.D. Student

Since Spring 2025


Powered by Jekyll and Minimal Light theme. Thanks for their excellent work.