Video Understanding
Modeling actions, intent, temporal structure, and long-form visual narratives.
Haopeng Li
PhD
I work at PICO, ByteDance, focusing on human visual perception. My research interests include video understanding, multimodal learning, reliable visual reasoning, and generative models.
Currently atPICO · ByteDance
RoleAI Algorithm Engineer
FocusHuman Visual Perception
EducationPhD, University of Melbourne
About Me
I am an AI Algorithm Engineer at PICO, ByteDance. I received my PhD from the University of Melbourne, supervised by Prof. Tom Drummond, Dr. Mingming Gong, and Dr. Qiuhong Ke. Before that, I studied mathematics and computer science at Northwestern Polytechnical University.
My research covers video understanding, vision-language learning, and reliable reasoning. My work has appeared at ICLR, ICML, ECCV, WACV, and in journals including T-PAMI, T-IP, T-MM, and IJCV.
Research Interests
Multimodal Learning
Aligning visual and language representations for grounded reasoning.
Reliable Reasoning
Helping models recognize uncertainty and answer within the limits of available evidence.
Generative Models
Developing agentic systems that interpret, segment, and interact with complex scenes.
Recent Work
SAM-Veteran: An MLLM-Based Human-like SAM Agent for Reasoning Segmentation
Tianyuan Du, Haopeng Li, Zhen Fan, Jiarui Zhang, Panwang Pan, Yang Zhang
Sports-QA: A Large-Scale Video Question Answering Benchmark for Complex and Professional Sports
Haopeng Li, Andong Deng, Jun Liu, Hossein Rahmani, Yulan Guo, Bernt Schiele, Mohammed Bennamoun, Qiuhong Ke
Answering from Sure to Uncertain: Uncertainty-Aware Curriculum Learning for Video Question Answering
Haopeng Li, Mohammed Bennamoun, Jun Liu, Hossein Rahmani, Qiuhong Ke
Admitting Ignorance Helps the Video Question Answering Models to Answer
Haopeng Li, Tom Drummond, Mingming Gong, Mohammed Bennamoun, Qiuhong Ke
Visual-Text Cross Alignment: Refining the Similarity Score in Vision-Language Models
Jinhao Li, Haopeng Li, Sarah Monazam Erfani, Lei Feng, James Bailey, Feng Liu
Progressive Video Summarization via Multimodal Self-supervised Learning
Haopeng Li, Qiuhong Ke, Mingming Gong, Tom Drummond
Experience & Education
Experience
PICO, ByteDance
AI Algorithm Engineer
Human Visual PerceptionMonash University
Research Assistant
Bridge competition cheating detectionThe University of Melbourne
Research Assistant
Sports video understandingSenseTime
Research Intern
Crowd video analysisEducation
PhD · Engineering and IT
The University of Melbourne
MSc · Computer Science and Technology
Northwestern Polytechnical University
BSc · Mathematics and Applied Mathematics
Northwestern Polytechnical University
Selected Honors
Melbourne Research Scholarship
The University of Melbourne
China National Scholarship
Ministry of Education of the PRC
Meritorious Winner
International Mathematical Contest in Modeling