Ling-An Zeng Bio Publications Services Awards CV
profile photo

Ling-An Zeng 曾令安

Ph.D. student

Sun Yat-sen University

Email: linganzeng@gmail.com

[G o o g l e   Scholar]   

Biography

I'm currently a 4th-year Ph.D. student at Sun Yat-sen University, advised by Prof. Wei-Shi Zheng. My research interests include video understanding and motion understanding and generation. I also have a strong interest in image and video generation .

Previously, I obtained my M.S. degree from Sun Yat-sen University in 2021, advised by Prof. Wei-Shi Zheng. Before that, I obtained my B.E. degree from the University of Electronic Science and Technology of China in 2019.

News

➤ [2025-03] One paper accepted in IEEE Transactions on Circuits and Systems for Video Technology (TCSVT).

➤ [2025-03] Two papers accepted in ICME 2025.

➤ [2025-02] One paper accepted in CVPR 2025.

➤ [2024-12] One paper accepted in AAAI 2025.

➤ [2024-07] One paper accepted in ECCV 2024.

➤ [2024-05] One paper accepted in IEEE Transactions on Circuits and Systems for Video Technology (TCSVT).

➤ [2024-04] One paper accepted in IEEE Transactions on Multimedia (TMM).

➤ [2024-02] One paper accepted in IEEE Transactions on Image Processing (TIP). .

➤ [2022-03] One paper accepted in CVPR 2022.

➤ [2020-07] One paper accepted in ACM Multimedia 2020.

Publications

Below are my publications. († Equal contribution; * Corresponding authors.)

PontTuset ChainHOI: Joint-based Kinematic Chain Modeling for Human-Object Interaction Generation
Ling-An Zeng†, Guohong Huang†, Yi-Lin Wei, Shengbo Gu, Yu-Ming Tang, Jingke Meng*, Wei-Shi Zheng*.
Conference on Computer Vision and Pattern Recognition (CVPR), 2025.
paper

ChainHOI: Text-driven human-object interaction generation with explicit joint and kinetic chain modeling for realistic results.

PontTuset Progressive Human Motion Generation Based on Text and Few Motion Frames
Ling-An Zeng, Gaojie Wu, Ancong Wu*, Jian-Fang Hu, Wei-Shi Zheng.
IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2025.
paper

Use text and few motion frames to achieve more accurate and controllable human motion generation.

PontTuset Light-T2M: A Lightweight and Fast Model for Text-to-motion Generation
Ling-An Zeng, Guohong Huang, Gaojie Wu, Wei-Shi Zheng*.
AAAI Conference on Artificial Intelligence (AAAI), 2025.
project / paper / code

Light-T2M: A Lightweight and Fast Model for Text-to-motion Generation.

PontTuset Multimodal action quality assessment
Ling-An Zeng, Wei-Shi Zheng*.
IEEE Transactions on Image Processing (TIP), 2024.
paper / code

PAMFN: State-of-the-art action quality assessment via adaptive fusion of RGB, optical flow, and audio.

PontTuset Hybrid Dynamic-static Context-aware Attention Network for Action Assessment in Long Videos
Ling-An Zeng, Fa-Ting Hong, Wei-Shi Zheng*, Qi-Zhi Yu, Wei Zeng, Yao-Wei Wang, Jian-Huang Lai.
ACM international conference on multimedia (ACM MM), 2020.
paper / code

ACTION-NET: State-of-the-art action quality assessment in long sports videos using hybrid dynamic-static modeling and attention, introducing the Rhythmic Gymnastics dataset.

PontTuset Efficient Explicit Joint-level Interaction Modeling with Mamba for Text-guided HOI Generation
Guohong Huang†, Ling-An Zeng†, Zexin Zheng, Shengbo Gu, Wei-Shi Zheng*.
IEEE International Conference on Multimedia & Expo (ICME), 2025.
Paper and code will be available soon.

EJIM: Efficient Mamba framework enabling explicit joint-level text-guided HOI generation with 5% inference time and superior results.

PontTuset AffordDexGrasp: Open-set Language-guided Dexterous Grasp with Generalizable-Instructive Affordance
Yi-Lin Wei†, Mu Lin†, Yuhao Lin, Jian-Jian Jiang, Xiao-Ming Wu, Liang-An Zeng, Wei-Shi Zheng*
arXiv, 2025.
paper

Open-Set Language-guided dexterous grasp based on generalizable-instructive Affordance.

PontTuset EgoExo-Fitness: Towards Egocentric and Exocentric Full-Body Action Understanding
Yuan-Ming Li†, Wei-Jin Huang†, An-Lan Wang†, Ling-An Zeng, Jing-Ke Meng*, Wei-Shi Zheng*
European Conference on Computer Vision (ECCV), 2024.
paper / code

EgoExo-Fitness: Synchronized egocentric and exocentric views for action understanding with action quality annotations.

PontTuset Adaptive Weight Generator for Multi-Task Image Recognition by Task Grouping Prompt
Gaojie Wu, Ling-an Zeng, Jing-Ke Meng*, Wei-Shi Zheng
IEEE Transactions on Multimedia (TMM), 2024.
paper

TGAW: Efficient multi-task image recognition via prompt-based automatic task grouping.

PontTuset Continual Action Assessment via Task-Consistent Score-Discriminative Feature Distribution Modeling
Yuan-Ming Li, Ling-An Zeng, Jing-Ke Meng*, Wei-Shi Zheng*.
IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2024.
paper / code

Continual-AQA: Enabling sequential learning in Action Quality Assessment without forgetting, using innovative rehearsal and graph-based techniques for superior performance.

PontTuset Likert Scoring With Grade Decoupling for Long-Term Action Assessment
Angchi Xu, Ling-An Zeng, Wei-Shi Zheng*.
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2022.
paper / code

GDLT: Quantifying performance grades in long-term action quality assessment for state-of-the-art results.

Services and Activities

Journal Reviewer:
Transactions on Machine Learning Research (TMLR)

Conference Reviewer:
CVPR, ICCV, ECCV, NeurIPS, ICLR, ICML, AAAI, ACM MM, ICME.

Honours and Awards

NeurIPS 2024 Outstanding Reviewer Award, 2024
Meritorious Winner, Mathematical Contest in Modeling, 2018
Gold Medal, ACM Sichuan Province Programming Contest, 2017
Bronze Medal, ICPC-ACM Programming Contest, Shenyang Regional Contest, 2017