Research

Our group conducts research in the following key areas:

  • Human Understanding and Analysis

  • Digital Health

  • Multimodal Large Foundation Models

  • Security, Privacy, and Trustworthiness in AI Applications

 

Some recent works in Human Understanding and Analysis

1. Xiaofei Hui, Haoxuan Qu, Hossein Rahmani, Jun Liu, An Image-like Diffusion Method for Human-Object Interaction Detection, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2025.

2. Haoxuan Qu, Yujun Cai, Jun Liu, LLMs are Good Action Recognizers, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2024.

3. Jia Gong, Lin Geng Foo, Zhipeng Fan, Qiuhong Ke, Hossein Rahmani, Jun Liu, DiffPose: Toward More Reliable 3D Pose Estimation, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2023.

 

Some recent works in Digital Health

1. Xiu Shu, Yunyun Yang, Jun Liu, Xiaojun Chang, Boying Wu, ALVLS: Adaptive local variances-Based levelset framework for medical images segmentation, Pattern Recognition (PR), 2023.

2. Xiaohong Wang, Xudong Jiang, Henghui Ding, Yuqian Zhao, Jun Liu, Knowledge-aware deep framework for collaborative skin lesion segmentation and melanoma recognition, Pattern Recognition (PR), 2021.

3. Xiaohong Wang, Xudong Jiang, Henghui Ding, Jun Liu, Bi-Directional Dermoscopic Feature Learning and Multi-Scale Consistent Decision Fusion for Skin Lesion Segmentation, IEEE Transactions on Image Processing (TIP), 2020.

 

Some recent works in Multimodal Large Foundation Models

1. Lanyun Zhu, Deyi Ji, Tianrun Chen, Haiyang Wu, De Wen Soh, Jun Liu, CPCF: A Cross-Prompt Contrastive Framework for Referring Multimodal Large Language Models, International Conference on Machine Learning (ICML), 2025.

2. Jia Gong, Lin Geng Foo, Yixuan He, Hossein Rahmani, Jun Liu, LLMs are Good Sign Language Translators, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2024.

3. Haoxuan Qu, Xiaofei Hui, Yujun Cai, Jun Liu, LMC: Large Model Collaboration with Cross-assessment for Training-Free Open-Set Object Recognition, Annual Conference on Neural Information Processing Systems (NeurIPS), 2023.

 

Some recent works in Security, Privacy, and Trustworthiness in AI Applications

1. Shuyang Hao, Bryan Hooi, Jun Liu, Kai-Wei Chang, Zi Huang, Yujun Cai, Exploring Visual Vulnerabilities via Multi-Loss Adversarial Search for Jailbreaking Vision-Language Models, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2025.

2. Duo Peng, Qiuhong Ke, Mark He Huang, Ping Hu, Jun Liu, Unified Prompt Attack Against Text-to-Image Generation Models, IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2025.

3. Duo Peng, Li Xu, Qiuhong Ke, Ping Hu, Jun Liu, Joint Attribute and Model Generalization Learning for Privacy-Preserving Action Recognition, Annual Conference on Neural Information Processing Systems (NeurIPS), 2023.