About

I am a first-year PhD student in Computer Science and Engineering at The Chinese University of Hong Kong (CUHK), supervised by Prof. Qiang Xu. I received my master’s degree and bachelor’s degree in computer science from Beijing Normal University (BNU), supervised by Prof. Saihui Hou and Prof. Yongzhen Huang.

Cooperation and discussion are welcome!

Research

My research focuses on vision-centric multimodal learning. Specifically:

Video Understanding and Generation: Omni-modal video models, currently focused on agentic generation.
Data & Evaluation: Data construction, captioning, and evaluation metrics for foundation models.
Visual Recognition: Core representation learning and understanding.

Publications

First-author Papers

Including co-first authorship (*).

Data Construction and Evaluation

VersusQ: Pairwise Margin Reasoning for Generalizable Video Quality Assessment

Shibei Meng, Binxin Yang, Yuan Liu, Jiexuan Zhang, Zhengyao Lv, Hubery Yin, Qiang Xu

Paper

A pairwise margin reasoning approach for generalizable video quality assessment, improving robustness across diverse domains.

RISE-Video: Can Video Generators Decode Implicit World Rules?

Mingxin Liu^*, Shuran Ma^*, Shibei Meng^*, Xiangyu Zhao^*, Zicheng Zhang, Shaofeng Zhang, Zhihang Zhong, Peixian Chen, Haoyu Cao, Xing Sun, Haodong Duan, Xue Yang

Paper Code

A benchmark evaluating whether video generation models can understand and follow implicit world rules during synthesis.

Recognition

From FastPoseGait to GPGait++: Bridging the Past and Future for Pose-based Gait Recognition

Shibei Meng^*, Yang Fu^*, Saihui Hou, Xuecai Hu, Chunshui Cao, Xu Liu, and Yongzhen Huang

TPAMI 2025Paper Code

An open-source toolbox for consistent gait recognition benchmarking, and a new method that is state-of-the-art in cross-domain scenarios.

Seeing from Magic Mirror: Contrastive Learning from Reconstruction for Pose-based Gait Recognition

Shibei Meng, Saihui Hou, Yang Fu, Xuecai Hu, Junzhou Huang, and Yongzhen Huang

ACM MM 2025Paper Code

A self-supervised 3D-aware pre-training framework that lifts 2D poses to 3D for large-scale contrastive learning in gait recognition.

GPGait: Generalized Pose-based Gait Recognition

Yang Fu^*, Shibei Meng^*, Saihui Hou, Xuecai Hu, and Yongzhen Huang

ICCV 2023Paper Code

A framework using Human-Oriented Transformation for unified pose representation, and a Part-Aware Graph Convolutional Network for cross-dataset generalization.

Coauthor Papers

IDC-RFT: Incentivizing Fine-Grained Image Difference Captioning via Reinforcement Fine-Tuning

Yuan Liu, Saihui Hou, Shibei Meng, Jiabao Du, and Yongzhen Huang

ACM MM 2026

OmniDiff: A Comprehensive Benchmark for Fine-grained Image Difference Captioning

Yuan Liu, Saihui Hou, Saijie Hou, Jiabao Du, Shibei Meng, and Yongzhen Huang

ICCV 2025Paper Dataset

Cut out the Middleman: Revisiting Pose-based Gait Recognition

Yang Fu, Saihui Hou, Shibei Meng, Xuecai Hu, Chunshui Cao, Xu Liu, and Yongzhen Huang

ECCV 2024Paper Code

Education

Aug 2026 – Present
Ph.D. in Computer Science and Engineering The Chinese University of Hong Kong (CUHK) Supervisor: Prof. Qiang Xu
Sep 2023 – Jul 2026
M.Eng. in Computer Science and Technology Beijing Normal University (BNU) Supervisors: Prof. Saihui Hou and Prof. Yongzhen Huang
Sep 2019 – Jul 2023
B.Eng. in Computer Science and Technology Beijing Normal University (BNU)

Honors and Awards

2025
National Scholarship
2025
BYD Scholarship
2024
First Prize, ACM MM'24 Multimodal Gait Recognition Challenge (Pose Track)
2023
Outstanding Undergraduate of Beijing Normal University