Scholar
Guo-Sen Xie
Google Scholar ID: LKaWa9gAAAAJ
Professor, Nanjing University of Science and Technology
Citations & Impact
Citations
4,261
H-index
31
i10-index
57
Publications
20
Co-authors
12
list available
Contact
No contact links provided.
Publications
Resume (English only)
Academic Achievements
- Authored/co-authored over 80 papers in top conferences/journals such as IEEE TPAMI, IJCV, CVPR, ICCV, and ECCV.
- Selected Papers:
- - SDE: A novel selective, discriminative and equalizing feature representation for visual recognition, IJCV, 2017
- - VMAN: A Virtual Mainstay Alignment Network for Transductive Zero-Shot Learning, TIP, 2021
- - Attentive region embedding network for zero-shot learning, CVPR, 2019
- - Few-Shot Semantic Segmentation with Cyclic Memory Network, ICCV, 2021
- - Region graph embedding network for zero-shot learning, ECCV, 2020
- - Task-driven Feature Pooling for Image Classification, ICCV, 2015
- - Leveraging Balanced Semantic Embedding for Generative Zero-Shot Learning, TNNLS, 2023
- - Generalized zero-shot learning with multiple graph adaptive generative networks, TNNLS, 2022
- - Hybrid CNN and Dictionary-Based Models for Scene Recognition and Domain Adaptation, TCSVT, 2017
Research Experience
- Researcher at Mohamed bin Zayed University of Artificial Intelligence from 2020 to 2022;
- Research Scientist at Inception Institute of Artificial Intelligence from 2018 to 2020;
- Currently a Professor at Nanjing University of Science and Technology (NJUST).
Education
- Ph.D. in Pattern Recognition and Intelligent System from Institute of Automation, Chinese Academy of Sciences (CASIA) in 2016, supervised by Prof. Cheng-Lin Liu;
- Visiting Research Student at National University of Singapore (NUS) from 2014 to 2015, supervised by Prof. Shuicheng Yan.
Background
- Research Interests: Computer vision, pattern recognition, and deep learning. Focused on the challenging problem of understanding complex visual data, such as cross-category, zero-/few-shot, and low-annotated data.
Miscellany
- Recruiting master's and doctoral students for 2026; can recruit 3-4 master's students and 1-2 doctoral students annually. Welcomes outstanding undergraduate students to participate in research projects.
