|
个人信息Personal Information
教师英文名称：Houjingyi
职称：讲师
学科：模式识别与智能系统
学位：博士
所在单位：智能科学与技术学院
电子邮箱：
- 侯静怡,齐雅昀,贾云得.跨语言知识蒸馏的视频中文字幕生成.计算机学报,2022,
- 侯静怡, 刘翠微, 吴心筱. 基于隐任务学习的动作识别方法. 北京理工大学学报, 2017..
- Jingyi Hou, Xinxiao Wu, Feiwu Yu, and Yunde Jia. Multimedia event detection via deep spatial-temporal neural networks. ICME, 2016. (oral presentation) （CCF B类会议）.
- Jingyi Hou, Xinxiao Wu, Jin Chen, Jiebo Luo, and Yunde Jia. Unsupervised Deep Learning of Mid-Level Video Representation for Action Recognition. AAAI, 2018. （顶级会议, CCF A）.
- Jingyi Hou, Xinxiao Wu, Xiaoxun Zhang, Yayun Qi, Jiebo Luo, and Yunde Jia. Joint Commonsense and Relation Reasoning for Image and Video Captioning. AAAI, 2020. （顶级会议, CCF A）.
- Jingyi Hou, Xinxiao Wu, Wentian Zhao, Jiebo Luo, and Yunde Jia. Joint Syntax Representation Learning and Visual Cue Translation for Video Captioning. ICCV, 2019. （顶级会议，CCF A）.
- Jingyi Hou, Xinxiao Wu, Yuchao Sun, and Yunde Jia. Content-Attention Representation by Factorized Action-Scene Network for Action Recognition. IEEE Transactions on Multimedia, 2018. （IF=5.551, 中科院一区, top期刊）.
- Jingyi Hou, Xinxiao Wu, Ruiqi Wang, Jiebo Luo, and Yunde Jia. Confidence-Guided Self Refinement for Action Prediction in Untrimmed Videos. IEEE Transactions on Image Processing. （IF=9.63, 中科院一区, top期刊）.
| |