个人简介
赵志伟，讲师，2024年6月博士毕业于中国科学技术大学，2025年1月起任合肥工业大学计算机与信息学院 (人工智能学院) 讲师。研究领域为计算机视觉、人工智能，研究方向包括多模态行人重识别、多模态大模型、AIGC。目前已在CCF-A类顶级会议和中科院一区IEEE Trans. 顶级期刊上发表了多篇学术论文，并担任ICLR、ACM MM、TCSVT等多个顶会顶刊的审稿人，参与了包括国自然面上项目、国家重点研发计划子课题在内的多个项目。曾任华为2012实验室的高级工程师，从事大模型算法相关的研发工作。目前所在的研究团队为合肥工业大学计算机与信息学院媒体计算实验室（由汪萌教授和洪日昌教授所领导)。
工作经历：
2025.01-至今，合肥工业大学计算机与信息学院，智能科学与技术系, 讲师
2024.08-2024.12，华为公司2012实验室，大模型算法，高级工程师
教育经历：
2019.09-2024.06, 中国科学技术大学，网络空间安全，博士
2015.09-2019.07，合肥工业大学, 通信工程, 本科
已发表学术论文：
1. Zhiwei Zhao, Bin Liu, Yan Lu, Qi Chu, Nenghai Yu. Unifying Multi-Modal Uncertainty Modeling and Semantic Alignment for Text-to-Image Person Re-identification. AAAI Conference on Artificial Intelligence, 2024. (AAAI2024, CCF-A类会议)
2. Zhiwei Zhao, Bin Liu, Yan Lu, Qi Chu, Nenghai Yu, Chang-Wen Chen. Joint Identity-aware Mixstyle and Graph-enhanced Prototype for Clothes-changing Person Re-identification. IEEE Transactions on Multimedia, 2023. (TMM, 中科院一区Top期刊)
3. Zhiwei Zhao, Bin Liu, Qi Chu, Yan Lu, Nenghai Yu. Joint Color-irrelevant Consistency Learning and Identity-aware Modality Adaptation for Visible-infrared Cross Modality Person Re-identification. (AAAI2021, CCF-A类会议)
4. Xuanpu Zhao, Dianmo Sheng, Zhentao Tan, Zhiwei Zhao, Tao Gong, Qi Chu, Bin Liu, Nenghai Yu. Training-free Open-Vocabulary Semantic Segmentation via Diverse Prototype Construction and Sub-region Matching. (AAAI2025, CCF-A类会议)
5. Yubo Wang, Bin Liu, Zhiwei Zhao, Jixiang Niu, Qi Chu, Nenghai Yu. CMGait: Enhancing Cross-Modality Gait Recognition between LiDAR and RGB through Contrastive Identity-consistent Feature Aggregation. International Conference on Acoustics, Speech and Signal Processing, 2025. (ICASSP2025, CCF-B类会议)
6. Jiazhen Wang, Bin Liu, Changtao Miao, Zhiwei Zhao, Wanyi Zhuang, Qi Chu, Nenghai Yu. Exploiting modality-specific features for multi-modal manipulation detection and grounding. International Conference on Acoustics, Speech and Signal Processing, 2024. (ICASSP2024, CCF-B类会议)
7. Zhangping Liu, Bin Liu, Zhiwei Zhao, Qi Chu, Nenghai Yu. Dual-uncertainty Guided Curriculum Learning and Partaware Feature Refinement for Domain Adaptive Person Re-identification. International Conference on Acoustics, Speech and Signal Processing, 2023. (ICASSP2023, CCF-B类会议)
8. Yaqi Zhang, Yan Lu, Bin Liu, Zhiwei Zhao, Qi Chu, Nenghai Yu. Evopose: A Recursive Transformer for 3D Human Pose Estimation with Kinematic Structure Priors. International Conference on Acoustics, Speech and Signal Processing, 2023. (ICASSP2023, CCF-B类会议)
9. Nan Ji, Bin Liu, Zhiwei Zhao, Yan Lu, Qi Chu, Zhenchao Jin, Nenghai Yu. Content-independent online handwriting verification based on multi-modal fusion. IEEE International Conference on Multimedia and Expo, 2021. (ICME2021, CCF-B类会议)