Yibing Song


Computer Vision Researcher
Tencent AI Lab

Email: yibingsong.cv at gmail dot com


Yibing Song currently works for Tencent. He has obtained PhD/Mphil degrees from City University of Hong Kong in 2018/2014 and a bachelor degree from University of Science and Technology of China in 2011. During graduate study, he has interned in Adobe Research, San Jose and visited UC Merced. Yibing Song focuses on the new trends of computer vision including self-supervised representation learning and adversarial attacks. Meanwhile, he is still interested in traditional topics including motion and tracking, visual recognition and generation.

Academic Service

Senior Program Committee: IJCAI 2021.

Outstanding Reviewer: CVPR 2018, CVPR 2019, CVPR 2020.

Top Reviewer: NeurIPS 2019.

3 Representative Publications   [More] [Citations]

VideoMoCo: Contrastive Video Representation Learning with Temporally Adversarial Examples,
Tian Pan, Yibing Song, Tianyu Yang, Wenhao Jiang, and Wei Liu,
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2021
[PDF|Project Page]
Unsupervised Deep Representation Learning for Real-Time Tracking,
Ning Wang, Wengang Zhou, Yibing Song, Chao Ma, Wei Liu, and Houqiang Li,
International Journal of Computer Vision (IJCV) 2020
[PDF|Project Page]
Rethinking Image Inpainting via a Mutual Encoder-Decoder with Feature Equalizations,
Hongyu Liu, Bin Jiang, Yibing Song, Wei Huang, and Chao Yang,
European Conference on Computer Vision (ECCV) 2020 (Oral)
[PDF|Project Page]