Zhu, Xinge 

Email: zhuxinge123 at gmail dot com

Biography

Xinge Zhu is pursuing his PhD degree at Multimedia lab, his supervisor is Prof. Dahua Lin. Before that, he received his B.E degree in 2015, from Shandong University.

His research interests include computer vision and deep learning, particularly in scene understanding and autonomous driving.

Publications

Depth Completion from Sparse LiDAR Data with Depth-Normal Constraints [PDF Coming soon]
Yan Xu, Xinge Zhu, Jianping Shi, Guofeng Zhang, Hujun Bao, Hongsheng Li
in ICCV 2019

Adapting Object Detectors via Selective Cross-Domain Alignment [PDF][Code]
Xinge Zhu, Jiangmiao Pang, Ceyuan Yang, Jianping Shi, Dahua Lin
in CVPR 2019

Not All Areas Are Equal: Transfer Learning for Semantic Segmentation via Hierarchical Region Selection [PDF]
Ruoqi Sun*, Xinge Zhu*, Chongruo Wu, Chen Huang, Jianping Shi, Lizhuang Ma
in CVPR 2019 (Oral)
*equal contribution

High Performance Gesture Recognition via Effective and Efficient Temporal Modeling [PDF][Code]
Yang Yi, Feng Ni, Yuexin Ma, Xinge Zhu, Yuankai Qi, Riming Qiu, Shijie Zhao, Feng Li, Yongtao Wang.
International Joint Conference on Artificial Intelligence (IJCAI), 2019

TrafficPredict: Trajectory Prediction for Heterogeneous Traffic-Agents [PDF] [Webpage][Dataset]
Yuexin Ma, Xinge Zhu, Sibo Zhang, Ruigang Yang, Wenping Wang, Dinesh Manocha
in AAAI 2019 (Oral)

Generative Adversarial Frontal View to Bird View Synthesis [PDF][Supp][Code]
Xinge Zhu, Zhichao Yin, Jianping Shi, Hongsheng Li, Dahua Lin.
in 3DV 2018

Penalizing Top Performers: Conservative Loss for Semantic Segmentation Adaptation [PDF][Supp]
Xinge Zhu, Hui Zhou, Ceyuan Yang, Jianping Shi, Dahua Lin.
in ECCV 2018

Pose Guided Human Video Generation [PDF]
Ceyuan Yang, Zhe Wang, Xinge Zhu, Chen Huang, Jianping Shi, Dahua Lin.
in ECCV 2018

Dependency Exploitation: A Unified CNN-RNN Approach for Visual Emotion Recognition [PDF]
Xinge Zhu, etc, Tianrong Rao, Dong Xu.
in IJCAI 2017

Image Tagging by Joint Deep Visual-Semantic Propagation [PDF]
Yuexin Ma, Xinge Zhu, Yujing Sun and Bingzheng Yan.
Best Paper Candidate of PCM 2017