三、代表性科研成果: [1] Zihan Ye,Fuyuan Hu*, Fan Lyu, Linyan Li, Kaizhu Huang*.Disentangling Semantic-To-Visual Confusion for Zero-Shot Learning[J]. IEEE Trans. on Multimedia, 2021,DOI: 10.1109/TMM.2021.3089017. [2] Fan Lyu#,Qi Wu#,Fuyuan Hu*, Qingyao Wu, Mingkui Tan. Attend and Imagine: Multi-Label Image Classifcation With Visual Attention and Recurrent Neural Networks[J]. IEEE Trans. on Multimedia, 2019, 21(8):1971-1981. (SCIE,Top) [3] Chaorui Deng#,QiWu#, Qingyao Wu*, Fan Lyu,Fuyuan Hu, Mingkui Tan*. Visual Grounding via Accumulated Attention[J]. IEEE Trans. on PAMI, 2020. DOI:10.1109/tpami.2020.3023438. (SCIE,Top) (Chaorui Deng#,QiWu#, Qingyao Wu*,Fuyuan Hu, Fan Lyu, Mingkui Tan*. Visual Grounding via Accumulated Attention[C]. CVPR, 2018.(CCF A类会议)) [4] Fan Lyu, Shuai Wang, Wei Feng*, Zihan Ye,Fuyuan Hu, Song Wang. Multi-Domain Multi-Task Rehearsal for Lifelong Learning[C]. AAAI,2021.(CCF A类会议, Accepted) [5]胡伏原,王振华,顾亚军,姒绍辉,吕凡,李林燕,李泽.一种基于分数阶微分估计梯度域的图像滤波方法. 2018(授权,ZL201510394348.8) [6]胡伏原,吴宏杰,姒绍辉.基于图像分割的深度不连续区域立体匹配算法.2017.(ZL201410113776.4) [7]胡伏原,李宏,崔志明,李林燕等.城市协同管理信息化平台建设及应用.江苏省科技进步奖三等奖,2017. [8]胡伏原,沈鸣飞,李林燕,夏振平等.智慧城市治理关键技术研究及应用.江苏省建设科技创新成果二等奖, 2020. [9]基于生成对抗网络的多模态数据协同生成方法研究,国家自然基金面上项目,主持,2019~2022年. [10]车载全景序列图像的特征匹配方法研究,国家自然基金面上项目,主持,2014~2018年. |