Fei Shen (沈飞) Ph.D. Candidate Nanjing University of Science and Technology National University of Singapore Office: Room 2003, CSE Building Email: feishen_at_njust.edu.cn Google Scholar • Github

About Me

Hi 😄! I am a member of the Intelligent Media Analysis Group (IMAG) and a Visiting Research Scholar at the National University of Singapore's NExT++ Center. I maintain close connections and collaborations with AIUNI, Mobvoi, , HuaWei, and Tencent in 2D/3D generation. My research interests lie in human-centered controlled and consistent generation, such as pose-guided person generation, virtual dressing/try-on, and talking face. I have been relentlessly striving to see humanity achieve digital immortality and machine consciousness at the earliest opportunity. Before this, I was a passionate algorithm competitor, achieving over 50 top-three finishes, including five first-place wins in CCF A Workshops. I am fervently dedicated to sharing🌱, collaborating🤝, advancing🚀, and innovating💡. I am deeply passionate about academic research and fully committed to utilizing my research findings to address real-world challenges, thereby making meaningful and impactful contributions to society. If you are interested in collaboration or wish to get in touch with me, please feel free to reach out via email! 😊

NEWS!

2025/01: Two papers ware accepted by ICLR 2025.
2024/12: Five papers ware accepted by AAAI 2025.
2024/11: We released IMAGPose, a unified conditional framework for pose-guided person generation.
2024/09: One paper was accepted by NeurIPS 2024.
2024/08: We released RCDMs for story visualization.
2024/05: We released IMAGDressing-v1 for customizable virtual dressing.
2024/05: We released V-Express for portrait video generation.
2024/02: We released PCDMs for pose-guided person synthesis.
2024/01: One paper was accepted by ICLR 2024.
2023/08: We won the 2nd place in Rotated Detection Challenge organized by IJCAI 2023 workshop.
2023/07: One paper was accepted by by ACM Multmedia 2023.
2023/03: We won the 1st place of Remote Sensing Image Segmentation Contest organized by NSFC.
2023/01: One paper was accepted by by IEEE T-IP (JCR Q1, IF=11.04).
2022/10: We again won 2nd place in the Global Campus AI Algorithms Challenge organized by HuaWei.
2022/10: I was selected as the publicity ambassador of the HDC
2022/05: We won the 3rd place in pet biometric Challenge organized by CVPR 2022 workshop.
2022/05: We won the 2nd place in few-shot logo detection challenge organized by ICME2022 workshop.
2022/03: One paper was accepted by ICME2022 (Oral).
2021/11: One paper was accepted by BMVC.
2021/09: One paper was accepted by IEEE IOTJ.
2021/06: One paper was accepted by IEEE T-ITS.
2020/05: We won the 1st place in COCO Detection Challenge organized by ECCV 2020 workshop.

Research Experience

  National University of Singapore, Singapore (May 2024 - Present)

• Visiting Research Scholar, NExT++
• Leader: Prof. Chua Tat-Seng

  Tencent Inc., Shenzhen China (May 2023 - May 2024)

• Intern, AI Lab (IP-Adapter Team)
• Leader: Dr. Xiao Han
• Mentor: Dr. Jun Zhang and Hu Ye

  Nanjing University of Science and Technology, Nanjing China

• PhD, IMAG
• Supervised by Prof. Jinhui Tang

All PublicationsShow selected

Selected PublicationsShow all

2025

Long-Term TalkingFace Generation via Motion-Prior Conditional Diffusion Model
Fei Shen, Cong Wang, Junyao Gao, Qin Guo, Jisheng Dang, Jinhui Tang, Tat-Seng Chua
Under Review [PDF] [Code] TL;DR: Proposed multilingual long-term talkingface.

FaceShot: Bring Any Character into Life
Junyao Gao, Yanan Sun, Fei Shen, Xin Jiang, Zhening Xing, Kai Chen, Cairong Zhao
ICLR 2025 [PDF] [Code]
TL;DR: Talkingface plugin for any character.

Ensembling Diffusion Models via Adaptive Feature Aggregation
Cong Wang, Kuan Tian, Yonghang Guan, Fei Shen, Zhiwei Jiang, Qing Gu, Jun Zhang
ICLR 2025 [PDF] [Code]
TL;DR: Uses routing aggregation for ensembling multiple diffusion models.

2024

IMAGDressing-v1: Customizable Virtual Dressing
Fei Shen, Xin Jiang, Xin He, Hu Ye, Cong Wang, Xiaoyu Du, Zechao Li, Jinhui Tang
AAAI 2025 [PDF] [Code]
TL;DR: Proposes the virtual dressing task and introduces a new dataset.

Boosting Consistency in Story Visualization with Rich-Contextual Conditional Diffusion Models
Fei Shen, Hu Ye, Sibo Liu, Jun Zhang, Cong Wang, Xiao Han, Wei Yang
AAAI 2025 [PDF] [Code]
TL;DR: Proposes non-autoregressive diffusion models for story generation.

V-Express: Conditional Dropout for Progressive Training of Portrait Video Generation
Cong Wang, Kuan Tian, Jun Zhang, Yonghang Guan, Feng Luo, Fei Shen, Zhiwei Jiang, Qing Gu, Xiao Han, Wei Yang
Under Review [PDF] [Code]
TL;DR: Explores strong and weak conditional relationships for portrait video generation.

IMAGPose: A Unified Conditional Framework for Pose-Guided Person Generation
Fei Shen and Jinhui Tang
NeurIPS 2024 [PDF] [Code]
TL;DR: Unifies person generation under diverse conditions.

2023

Advancing Pose-Guided Image Synthesis with Progressive Conditional Diffusion Models
Fei Shen, Hu Ye, Jun Zhang, Cong Wang, Xiao Han, Wei Yang
ICLR 2024 [PDF] [Code]
TL;DR: Introduces concat/inpainting methods for generation.

Triplet Contrastive Representation Learning for Unsupervised Vehicle Re-identification
Fei Shen, Xiaoyu Du, Liyan Zhang, Xiangbo Shu, and Jinhui Tang
TOMM 2024 [PDF] [Code]

Pedestrian-specific Bipartite-aware Similarity Learning for Text-based Person Retrieval
Fei Shen, Xiangbo Shu, Xiaoyu Du, and Jinhui Tang
ACM Multmedia 2023 [PDF] [Code]

GiT: Graph interactive transformer for vehicle re-identification
Fei Shen, Yi Xie, Jianqing Zhu, Xiaobin Zhu, and Huanqiang Zeng
IEEE Transactions on Image Processing [PDF] [Code]

2022

HSGM: A hierarchical similarity graph module for object re-identification
Fei Shen, Xiaoxiao Peng, Lisheng Wang, Xingmeng Hao, Mei Shu, and Yajun Wang
IEEE ICME 2022 [PDF] [Code]

Enhancing part features via contrastive attention module for vehicle re-identification
Manyu Li, Mengwan Wei, Xin He, and Fei Shen*
IEEE ICIP 2022 [PDF] [Code]

A Novel Multi-Frequency Coordinated Module for SAR Ship Detection
Chenchen Qiao, Fei Shen, Xuejun Wang, Ruixin Wang, Fang Cao, Sixian Zhao, and Chang Li
IEEE ICTAI 2022 [PDF] [Code]

A sample-proxy dual triplet loss function for object re-identification
Hanxiao Wu, Fei Shen, Jianqing Zhu, Huanqiang Zeng, Xiaobin Zhu, and Zhen Lei
IET Image Processing [PDF] [Code]

2021

Exploring spatial significance via hybrid pyramidal graph network for vehicle re-identification
Fei Shen, Jianqing Zhu, Xiaobin Zhu, Yi Xie, and Jingchang Huang
IEEE Transactions on Intelligent Transportation Systems [PDF] [Code]

An efficient multiresolution network for vehicle reidentification
Fei Shen, Jianqing Zhu, Xiaobin Zhu, Jingchang Huang, Huanqiang Zeng, Zhen Lei, and Canhui Cai
IEEE Internet of Things Journal [PDF] [Code]

Object Re-identification Using Teacher-Like and Light Students
Yi Xie, Hanxiao Wu, Fei Shen, Jianqing Zhu, and Huanqiang Zeng
BMVC 2021 [PDF] [Code]

Viewpoint robust knowledge distillation for accelerating vehicle re-identification
Yi Xie, Fei Shen, Jianqing Zhu, and Huanqiang Zeng
EURASIP Journal on Advances in Signal Processing [PDF] [Code]

Honors

Professional Services

Others