Wenzheng Zeng 「曾文正」

I am a first year PhD candidate at the National University of Singapore (NUS), affiliated with the Department of Computer Science and Show Lab, closely co-supervised by Prof. Hwee Tou Ng and Prof. Mike Zheng Shou. I received my B.Eng and M.Phil degree from School of Artificial Intelligence and Automation, Huazhong University of Science and Technology (HUST), working with Prof. Yang Xiao and Prof. Zhiguo Cao, and also collaborating with Dr. Joey Tianyi Zhou and Prof. Junsong Yuan. I work on computer vision research, with a primary focus on multimodal and spatiotemporal intelligence. Email | Google Scholar | X (Twitter) | Github | 知乎

• 
  SlideTailor: Personalized Presentation Slide Generation for Scientific Papers

  Wenzheng Zeng*, Mingyu Ouyang*, Langyuan Cui*, Hwee Tou Ng‡
  AAAI 2026

  [Paper] [Code] [Poster] [Video] [Slides]
• 
  Factorized Learning for Temporally Grounded Video-Language Models

  Wenzheng Zeng, Difei Gao, Mike Zheng Shou‡, Hwee Tou Ng‡
  ICCV 2025

  [Paper] [Code] [Poster] [Video]
• 
  MP-Mat: A 3D and Instance-Aware Human Matting and Editing Framework with Multiplane Representation

  Siyi Jiao*, Wenzheng Zeng*†, Yerong Li, Huayu Zhang, Changxin Gao, Nong Sang‡, Mike Zheng Shou‡
  ICLR 2025

  [Paper] [Code]
• 
  DFIMat: Decoupled Flexible Interactive Matting in Multi-Person Scenarios

  Siyi Jiao*, Wenzheng Zeng*, Changxin Gao, Nong Sang
  ACCV 2024

  [Paper] [Code]
• 
  CrossGLG: LLM Guides One-shot Skeleton-based 3D Action Recognition in a Cross-level Manner

  Tingbing Yan, Wenzheng Zeng‡, Yang Xiao‡, Xingyu Tong, Bo Tan, Zhiwen Fang, Zhiguo Cao, Joey Tianyi Zhou
  ECCV 2024

  [Paper] [Code]
• 
  End-to-End Video Gaze Estimation via Capturing Head-Face-Eye Spatial-Temporal Interaction Context

  Yiran Guan*, Zhuoguang Chen*, Wenzheng Zeng‡, Zhiguo Cao, Yang Xiao‡
  IEEE Signal Processing Letters, 2023

  [Paper] [Code]
• 
  Real-time Multi-person Eyeblink Detection in the Wild for Untrimmed Video

  Wenzheng Zeng, Yang Xiao, Sicheng Wei, Jinfang Gan, Xintao Zhang, Zhiguo Cao, Zhiwen Fang, Joey Tianyi Zhou
  CVPR 2023

  [Project Page] [Paper] [Video] [Poster] [Code] [Dataset]
• 
  Eyelid’s Intrinsic Motion-aware Feature Learning
  for Real-time Eyeblink Detection in the Wild

  Wenzheng Zeng, Yang Xiao, Guilei Hu, Zhiguo Cao, Sicheng Wei, Zhiwen Fang,
  Joey Tianyi Zhou, Junsong Yuan
  IEEE Transactions on Information Forensics and Security (TIFS), 2023

  [Paper] [Code]

Invited Talk

• 
  Invited poster and spotlight talk at CVPR GAZE2023 workshop.

  Topic: Multi-person eyeblink detection in the wild in untrimmed videos.

Competitions

(Team leader or core contributor)

• 
  The "Challenge Cup" National Competition, 2023

  Topic: Driver Monitoring System (DMS).

  Result: Winning the Grand Prize (top prize beyond First Prize), serving as team leader.
• 
  The Visual Inductive Priors for Data-Efficient Computer Vision Challenge, ECCV 2022

  Topic: Action recognition with limited training data.

  Result: Obtain 3rd place and Jury Prize in the action recognition track (equal core contribution).
• 
  China Graduate AI Innovation Competition, 2021

  Topic: Cloud + AI assist Parkinson's Diagnosis.

  Result: Obtain 3rd place and fisrt prize (3/1505).
• 
  Fisheye Video-based Action Recognition Competition at the MMVRAC Workshop, ICCV 2021

  Topic: Action recognition in fisheye videos.

  Result: Obtain 4th place.
• 
  The Mathematical Contest In Modeling (MCM), America, 2020

  Topic: Comprehensive exploration of buyer reviews and ratings for Amazon e-commerce products.

  Result: Obtain Meritorious Winner (9%) (equal core contribution).

Selected Awards

• Research Achievement Award, School of Computing, NUS, 2025-2026
• PhD Research Scholarship, NUS, 2024
• PhD Fellowship, UCSD, 2024
• National Scholarship (Rank 1/600+), 2023
• HUAWEI Scholarship (Rate < 1%), 2023
• Outstanding Undergraduate, 2021
• Outstanding Undergraduate Thesis (Rate < 3% in HUST), 2021