承担的科研课题
1.国家自然科学基金重点项目:知识驱动的复杂场景多模态语义理解理论与方法.(合作单位负责人)
2.北京市自然科学基金-小米联合基金重点项目:以语言为核心的多模态大模型及其在图文理解与生成中的评价与应用(课题负责人)
3.国家自然科学基金面上项目:融合运动模式和群体交互特征的体育视频语义事件识别(项目负责人)
4.北京市自然科学基金-北京市教委联合资助重点项目:大尺寸面曝光快速成型关键技术和系统(项目负责人)
5.北京市自然科学基金-北京市教委联合资助重点项目:基于多模态数据的广义分层二部图推荐算法(项目负责人)
6.北京市自然科学基金京津冀基础研究项目:融合智能信息处理的大尺度面曝光3D打印关键技术研究(项目负责人)
代表性论文
1.Lifang Wu, Meng Tian, Ye Xiang, Ke Gu, Ge Shi. Learning label semantics for weakly supervised group activity recognition. IEEE Transactions on Multimedia, 26: 6386-6397, 2024.(JCR Q1)
2.Zhuming Wang, Zun Li, Xianglong Lang, Yihao Zheng, Meng Tian,Lifang Wu#, Liang Wang, Changwen Chen. Knowledge Augmented Relation Inference for Group Activity Recognition. IEEE Transactions on Circuits and Systems for Video Technology, 34(11): 1164.4-11656, 2024.(JCR Q1)
3.Zhao LD, Zhao Z, Ma LM, Men ZN, Ma YK,Wu LF. Limiting defect in vat photopolymerization via visual-guided in-situ repair[J]. Additive Manufacturing, 2024, 79: 103947.(JCR Q1)
4.Deng Sinuo,Wu Lifang, Shi Ge#. Simple but Powerful, a Language-Supervised Method for Image Emotion Classification.IEEE Transactions on Affective Computing,2022.DOI:10.1109/TAFFC.2022.3225049(JCR Q1)
5.Wu Lifang, Yang Zhou, Jian Meng#, Shen Jialie, Yang Yuchen, Lang Xianglong.Global motion estimation with iterative optimization-based independent univariate model for action recognition,Pattern Recognition, vol.116, pp. 107925, 2021.(JCR Q1)
6.Yuchen Yang, Ye Xiang, Shuaicheng Liu,Lifang Wu#, Boxuan Zhao, and Bing Zeng. GLM-Net: Global and Local Motion Estimation via Task-Oriented Encoder-Decoder Structure.ACM International Conference on Multimedia. pp.4211-4219, 2021. (CCF A类会议)
7.Jian Meng, Guo Jingjing, Zhang Chenlin, Jia Ting,Wu Lifang. Yang Xun, Huo Lina. Semantic manifold modularization-based ranking for image recommendation,Pattern Recognition, vol.120, pp. 108100, 2021.(JCR Q1)
8.Zhuming Wang, Yaowen Xu,Lifang Wu#, Hu Han, Yukun Ma and Guozhang Ma. Multi-Perspective Features Learning for Face Anti-Spoofing[C]. 2021IEEE/CVF International Conference on Human Centered Computer Vision Workshops, 2021: 4099-4105 (Best Paper)