视觉语言模型，多模态预训练
博士后科学基金第71批面上资助
基于跨模态预训练的图文理解与生成方法研究（国家自然科学基金/青年科学基金项目）
Multi-camera multi-player tracking with deep player identification in sports video
Noise augmented double-stream graph convolutional networks for image captioning
Recall what you see continually using gridlstm in image captioning
Image to Modern Chinese Poetry Creation via A Constrained Topic-Aware Model
Appearance features in Encoding Color Space for visual surveillance
Person re-identification via rich color-gradient feature
中国科学院特别研究助理资助项目
2022年度博士后国际交流计划引进项目（第一批)
图像生成方法、装置和电子设备
