Email: peterxu1986@foxmail.com
CV(EN) / CV(CN)(Coming Soon), LinkedIn.
Last update：July 2021
202106 Hiring for 2022 graduates are now open
202106 华为诺亚方舟实验室终端视觉团队在MIT Scene Parsing Benchmark荣获第一
Songcen Xu received his Bachelor Degree in Wuhan University of Technology in China in 2008, and the M.Sc. degree in communications engineering and the Ph.D. degree in electronic engineering from the University of York, York, U.K., in 2011 and 2015, respectively.
My research mainly focus on Computer Vision and their applications on mobile device.
Specifically, my current research interests include:
Generating Diverse Structure for Image Inpainting With Hierarchical VQ-VAE
Jialun Peng, Dong Liu, Songcen Xu, Houqiang Li
IEEE Conference on Computer Vision and Pattern Recognition. 2021
Multiple Instance Active Learning for Object Detection
Tianning Yuan, Fang Wan, Mengying Fu, Jianzhuang Liu, Songcen Xu, Xiangyang Ji, Qixiang Ye
IEEE Conference on Computer Vision and Pattern Recognition. 2021
Agreement-Discrepancy-Selection: Active Learning with Progressive Distribution Alignment
Mengying Fu, Tianning Yuan, Fang Wan, Songcen Xu, Qixiang Ye
AAAI Conference on Artificial Intelligence. 2021
Renovating Parsing R-CNN for Accurate Multiple Human Parsing
Lu Yang, Qing Song, Zhihui Wang, Mengjie Hu, Chun Liu, Xueshi Xin, Wenhe Jia, Songcen Xu
European Conference on Computer Vision. 2020
Index Network
Hao Lu, Yutong Dai, Chunhua Shen, Songcen Xu
IEEE Transactions on Pattern Analysis and Machine Intelligence. 2020.
DiverseDepth: Affine-invariant Depth Prediction Using Diverse Data
Wei Yin, Xinlong Wang, Chunhua Shen, Yifan Liu, Zhi Tian, Songcen Xu, Changming Sun, Dou Renyin
arxiv. 2020
Indices Matter: Learning to Index for Deep Image Matting
Hao Lu, Yutong Dai, Chunhua Shen, Songcen Xu
International Conference on Computer Vision. 2019