主要研究方向
.视觉语言多模态学习、异常检测

研究领域
.视觉语言多模态学习
.异常检测

代表作
.Cao M, Li S, Li J, et al. Image-text Retrieval: A Survey on Recent Research and Development[J]. International Joint Conference on Artificial Intelligence (IJCAI), 2022
.Cao M, Ding C, Chen C, et al. Progressive Context-aware Graph Feature Learning for Target Re-identification[J]. IEEE Transactions on Multimedia (TMM), 2022
.Li S, Cao M*, Zhang M. Learning Semantic-Aligned Feature Representation for Text-Based Person Search[C]//ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2022: 2724-2728
.Wang Y, Cao M, Fan Z, Peng S, Learning to detect 3D facial landmarks via heatmap regression with Graph Convolutional Network[C]//AAAI Conference on Artificial Intelligence. 2021
.Cao M, Chen C, Dou H, et al. Progressive Bilateral-Context Driven Model for Post-Processing Person Re-Identification[J]. IEEE Transactions on Multimedia (TMM), 2020, 23: 1239-1251

个人简介

曹敏，女，副教授，硕士生导师。2020年1月于中国科学院自动化研究所获得工学博士学位，从事研究方向主要是视觉语言多模态学习、异常检测。2020年3月入职古天乐代言太阳集团。目前已发表10余篇人工智能国际顶级会议与期刊论文，并主持国家自然科学青年基金1项，人工智能教育部重点实验室开放课题1项。