🧍‍♂️About-me

My name is Jinfu Liu. I am currently an algorithm engineer at DJI. My work focuses on developing On-device AI Technologies and integrating them into DJI’s product lines, including the Drone series and the OSMO series.
Prior to that, I received my M.S. degree in Sun Yat-sen University (supervised by Prof.Mengyuan Liu), where my research are primarily focused on Video Understanding. I received my B.S. degree in Automation from Wuhan University of Technology.
During my studies, I was also an intern at Tencent AMS, MeiTuan, and Tencent AI Lab, where I gained experience in business scenarios such as advertising, e-commerce, and gaming. My research involved content understanding, video generation, and digital human generation.
Now my research interests are primarily focused on Video Understanding, On-device AI Technologies, and Content Generation. I was also a reviewer in the aforementioned fields (e.g. in the IEEE-TPAMI, IEEE-TMM, IEEE-TCSVT, ECCV, ACM MM, and ICME).

🔥News

2025.12: 🎉 One paper is accepted by TPAMI 2025.
2025.06: 🎉 One paper is accepted by IROS 2025.
2025.06: 🎉 Received the Outstanding Graduate honor.
2024.07: 🎉 One paper is accepted by ACM MM 2024.
2024.01: 🎉 One paper is accepted by TMM 2024.

📖Experience

2025.06-Now: Algorithm Engineer in DJI Imaging Department, Shenzhen, China
2025.01-2025.03: Algorithm Intern in Tencent AMS, Shenzhen, China
2024.05-2024.08: Algorithm Intern in Meituan, Beijing, China
2023.12-2024.05: Algorithm Intern in Tencent AI Lab, Shenzhen, China
2022.04-2022.08: Algorithm Intern in Civicint, Shenzhen, China

📖Education

2022.09-2025.06: M.S. in Sun Yat-sen University, Shenzhen, China
2018.09-2022.06: B.S. in Wuhan University of Technology, Wuhan, China

📝Main Publications

* indicates equal contribution. # indicates corresponding author.

Mengyuan Liu, Jinfu Liu#, Yongkang Jiang, Bin He. Heatmap Pooling for Action Recognition from RGB Videos. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2025. (CCF A) [Paper] [Code]
Baiqiao Yin, Jiaying Lin, Jiajun Wen, Yue Li, Jinfu Liu, Yanfei Wang, Mengyuan Liu#. Recognizing Skeleton-Based Actions As Points. IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2025. (CCF C Oral) [Paper] [Code]
Jinfu Liu, Chen Chen, Mengyuan Liu#. Multi-Modality Co-Learning for Efficient Skeleton-based Action Recognition. ACM Multimedia (ACM MM), 2024. (CCF A) [Paper] [Code] [Poster]
Jinfu Liu, Xinshun Wang, Can Wang, Yuan Gao, Mengyuan Liu#. Temporal Decoupling Graph Convolutional Network for Skeleton-based Gesture Recognition. IEEE Transactions on Multimedia (TMM), 2024. (CCF B) [Paper] [Code]
Jinfu Liu*, Runwei Ding*, Yuhang Wen, Nan Dai, Fanyang Meng, Fang-Lue Zhang, Shen Zhao, Mengyuan Liu#. Explore Human Parsing Modality for Action Recognition. CAAI Transactions on Intelligence Technology (TRIT), 2024. (JCR Q1) [Paper] [Code]
Jinfu Liu*, Baiqiao Yin*, Jiaying Lin, Jiajun Wen, Yue Li, Mengyuan Liu#. HDBN: A Novel Hybrid Dual-branch Network for Robust Skeleton-based Action Recognition. International Conference on Multimedia and Expo Workshop (ICMEW), 2024. (CCF B Competition) [Paper] [Code]
Jiaying Lin*, Jiajun Wen*, Mengyuan Liu#, Jinfu Liu, Baiqiao Yin, Yue Li. SFMViT: SlowFast Meet ViT in Chaotic World. International Conference on Multimedia and Expo Workshop (ICMEW), 2024. (CCF B Competition) [Paper] [Code]
Yue Li, Baiqiao Yin, Jinfu Liu, Jiajun Wen, Jiaying Lin, Mengyuan Liu#. SemiPL: A Semi-supervised Method for Event Sound Source Localization. International Conference on Multimedia and Expo Workshop (ICMEW), 2024. (CCF B Competition) [Paper] [Code]
Runwei Ding*, Yuhang Wen*, Jinfu Liu, Nan Dai, Fanyang Meng, Mengyuan Liu#. Integrating Human Parsing and Pose Network for Human Action Recognition. CAAI International Conference on Artificial Intelligence (CICAI), 2023. (CAAI A Oral) [Paper] [Code] [Poster]

🎖Honors and Awards

Outstanding Graduate of Sun Yat-sen University (Top-5%) (2025).
The First Prize Scholarship of Sun Yat-sen University. (2022, 2023, 2024)
Champion of ICME Grand Challenge Multi-Modal Video Reasoning and Analyzing Competition. (2024)
Outstanding Graduate of Wuhan University of Technology. (2022)
The First Prize Scholarship and Merit Student of Wuhan University of Technology (Top-3%) (2020, 2021).