当前位置:首页 > 全体教师
傅建龙
单 位:微软亚洲研究院
职 务:高级研究员
职 称:教授(博士生导师)
通信地址: 北京市海淀区丹棱街5号
邮 编:100083
办公地点:微软大厦
办公电话:010-59165640
电子邮件:jianf@microsoft.com
社会职务:永利集团3044官网欢迎您兼职教授、2021年国际多媒体大会(ACM Multimedia)工业领域分会主席、2018-2021年IEEE Transactions on PAMI客座编委
- 教育背景
- 工作履历
- 研究方向
- 代表性论著
- 成果、荣誉
- 发明专利
2006-09至2010-07 永利集团3044官网欢迎您信息工程学院 学士
2010-09至2015-07 中国科学院自动化研究所 模式识别与智能系统专业 博士
2015-07至2017-08 微软亚洲研究院 副研究员
2017-09至2018-11 微软亚洲研究院 研究员
2018-12至今 微软亚洲研究院 高级研究员,多媒体组负责人
精细化图像视频理解
图像视频生成与增强
视觉与语言
【代表性科研论文】
[1] Zhicheng Huang, Zhaoyang Zeng, Yupan Huang, Bei Liu, Dongmei Fu, Jianlong Fu. Seeing Out of the Box: End-to-End Pre-training for Vision-Language Representation Learning. The Conference on Computer Vision and Pattern Recognition (CVPR), 2021 (Oral).
[2] Zhaoyang Zeng, Bei Liu, Jianlong Fu, Hongyang, Chao. Reference-based Defect Detection Network. IEEE Transactions on Image Processing (TIP), 2021 (通讯作者).
[3] Houwen Peng, Hao Du, Hongyuan Yu, Jing Liao, and Jianlong Fu. Distilling Prioritized Paths for One-shot Neural Architecture Search. NeurlPS, 2020 (通讯作者).
[4] Yanhong Zeng, Jianlong Fu, Hongyang Chao. Learning Joint Spatial-Temporal Transformations for Video Inpainting. European Conference on Computer Vision (ECCV), 2020 (通讯作者).
[5] Jianbo Wang, Kai Qiu, Houwen Peng, Jianlong Fu, Jianke Zhu. AI Coach: Deep Human Pose Estimation and Analysis for Personalized Athletic Training Assistance. ACM Multimedia, 2019 (通讯作者).
[6] Bei Liu, Jianlong Fu, Makoto P. Kato, Masatoshi Yoshikawa. Beyond Narrative Description: Generating Poetry from Images by Multi-Adversarial Training. ACM Multimedia, 2018 (通讯作者,最佳会议论文).
[7] Jianlong Fu, Heliang Zheng, Tao Mei. Look Closer to See Better: Recurrent Attention Convolutional Neural Network for Fine-grained Image Recognition. Computer Vision and Pattern Recognition (CVPR), 2017 (Oral, google scholar引用714次).
[8] Heliang Zheng, Jianlong Fu, Tao Mei, Jiebo Luo. Learning multi-attention convolutional neural network for fine-grained image recognition. International Conference on Computer Vision (ICCV), 2017 (Oral, google scholar引用488次)
【专著成果】
[1] Jianlong Fu, Tao Mei. Image Tagging with Deep Learning: Fine-grained Visual Analysis. Book Chapter in “Big Data Analytics for Large-Scale Multimedia Search" (published by Wiley & Sons in 2018)
1. 2019年ActivityNet Dense Captioning 国际挑战赛第一名
2. 2019年Visual Question Answering国际挑战赛第二名
3. 2018年ACM Multimedia会议最佳论文
[1] Tao Mei, Jianlong Fu, Kuiyuan Yang, Yong Rui. Tagging personal photos with deep networks. United State Patent No.9754188B2.
[2] Jianlong Fu, Tao Mei. Fine-grained image recognition. United State Patent No. 20200160124A1.