I am a forth-year Ph.D. student (expected 2025) in the Department of Computer Science at Shanghai Jiao Tong University. Currently, I am a member of the SJTU MVIG under the supervision of Prof. Cewu Lu. Prior to that, I received my Bachelor’s degree (Computer Science) from Shanghai Jiao Tong University in 2020. My research interests mainly lie in motion/action prediction under embodied environments for autonomous driving, robots and digital human.

I am always open for collaborations and if you are interested in my research feel free to contact me via email.

Publications

Modality Exploration, Retrieval and Adaptation for Trajectory Prediction
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)
Jianhua Sun, Yuxuan Li, Liang Chai, Cewu Lu

InstaBoost++: Visual Coherence Principles for Unified 2D/3D Instance Level Data Augmentation
International Journal of Computer Vision (IJCV)
Jianhua Sun*, Hao-Shu Fang*, Yuxuan Li, Runzhong Wang, Minghao Gou and Cewu Lu

Stimulus Verification is a Universal and Effective Sampler in Multi-Modal Human Trajectory Prediction
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023
Jianhua Sun*, Yuxuan Li*, Liang Chai, Cewu Lu
paper / code

Human Trajectory Prediction with Momentary Observation
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022
Jianhua Sun, Yuxuan Li, Liang Chai, Hao-Shu Fang, Yong-Lu Li, Cewu Lu
paper / code

Correlation Field for Boosting 3D Object Detection in Structured Scenes
AAAI Conference on Artificial Intelligence (AAAI), 2022
Jianhua Sun, Hao-Shu Fang, Xianghui Zhu, Jiefeng Li, Cewu Lu
paper

Unified and Fast Human Trajectory Prediction Via Conditionally Parameterized Normalizing Flow
IEEE Robotics and Automation Letters (RA-L)
Jianhua Sun, Zehao Wang, Jiefeng Li, Cewu Lu
paper

Three Steps to Multimodal Trajectory Prediction: Modality Clustering, Classification and Synthesis
IEEE/CVF International Conference on Computer Vision (ICCV), 2021
Jianhua Sun, Yuxuan Li, Hao-Shu Fang, Cewu Lu
paper / code

Recursive Social Behavior Graph for Trajectory Prediction
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020
Jianhua Sun, Qinhong Jiang, Cewu Lu
paper

Instaboost: Boosting Instance Segmentation via Probability Map Guided Copy-Pasting
IEEE/CVF International Conference on Computer Vision (ICCV), 2019
Hao-Shu Fang*, Jianhua Sun*, Runzhong Wang*, Minghao Gou, Yonglu Li, Cewu Lu
paper / code

Symbol-LLM: Leverage Language Models for Symbolic System in Visual Human Activity Reasoning
Conference on Neural Information Processing Systems (NeurIPS), 2023
Xiaoqian Wu, Yong-Lu Li, Jianhua Sun, Cewu Lu

Selected Awards

CCF-CV Outstanding Young Researcher Award (CCF-CV学术新锐, 3 in China)
Baidu Scholarship Top20
ByteDance Scholars, Finalist
National Scholarship (Ph.D. & Undergraduate)
Yang Yuanqing Scholarship (Ph.D. & Undergraduate, 3 in SJTU)
Wu Wenjun Honor Ph.D. Student, SJTU
SenseTime Scholarship
Shanghai Outstanding Undergraduate

Services

Reviewer of Nature Machine Intelligence, TMM, CVPR, ICCV, ECCV, AAAI, IROS, etc.