Linjie Yang

I am currently a Research Scientist at ByteDance Inc. in Mountain View, CA. Before that, I was a Research Scientist at Snap Research during 2016 - 2018. I obtained my PhD degree in the department of Information Engineering, Chinese University of Hong Kong in July 2016. I was supervised by Prof. Xiaoou Tang and Prof. Jianzhuang Liu. I also worked closely with Prof. Chen Change Loy and Ping Luo. I obtained my bachelor's degree from the department of Electronic Engineering, Tsinghua University in 2012. I worked as a research intern in Microsoft Research Asia from November 2011 to April 2012. My research interests include computer vision and machine learning, especially visual understanding with deep learning.

We are actively looking for full-time research scientists / engineers as well as research interns on computer vision and deep learning. Drop me an email if you are interested!

Recent Activities

  • I am co-organizing The 4th Large-scale Video Object Segmentation Challenge in conjunction with CVPR 2022. We have the same three tracks as last year: video object segmentation, video instance segmentation and language referring video segmentation. VIS is augmented with challenging long video settings! Call for participants!

  • Our paper with a new benchmark for multi-task neural architecture search accepted by ICLR 2022.

  • One paper on Video Matting accepted by WACV 2022. New SOTA!

  • One paper on Neural Architecture Search accepted by ICCV 2021.

  • Two papers accepted by CVPR 2021, including one oral (HR-NAS) and one poster (SOTA on Video Inpainting).



Learning Versatile Neural Architectures by Propagating Network Codes

Mingyu Ding, Yuqi Huo, Haoyu Lu, Linjie Yang, Zhe Wang, Zhiwu Lu, Jingdong Wang, Ping Luo

ICLR 2022. arXiv OpenReview Code

Robust High-Resolution Video Matting with Temporal Guidance

Shanchuan Lin, Linjie Yang, Imran Saleemi, Soumyadip Sengupta

WACV 2022. arXiv Project


AutoSpace: Neural Architecture Search with Less Human Interference

Daquan Zhou, Xiaojie Jin, Xiaochen Lian, Linjie Yang, Yujing Xue, Qibin Hou, Jiashi Feng

ICCV 2021. arXiv

Progressive Temporal Feature Alignment Network for Video Inpainting

Xueyan Zou, Linjie Yang, Ding Liu, Yong Jae Lee

CVPR 2021. arXiv Code

HR-NAS: Searching Efficient High-Resolution Neural Architectureswith Lightweight Transformers

Mingyu Ding, Xiaochen Lian, Linjie Yang, Peng Wang, Xiaojie Jin, Zhiwu Lu, Ping Luo

CVPR 2021 (Oral).

CompFeat: Comprehensive Feature Aggregation for Video Instance Segmentation

Yang Fu, Linjie Yang, Ding Liu, Thomas S. Huang, Humphrey Shi

AAAI 2021. arXiv

FracBits: Mixed Precision Quantization via Fractional Bit-Widths

Linjie Yang*, Qing Jin*

AAAI 2021. arXiv


Neural Network Quantization with Scale-Adjusted Training

Qing Jin, Linjie Yang, Zhenyu Liao, Xiaoning Qian

BMVC 2020. arXiv Version Conference Version Supplementary Code

Neural Architecture Search for Lightweight Non-local Networks

Yingwei Li, Xiaojie Jin, Jieru Mei, Xiaochen Lian, Linjie Yang, Cihang Xie, Qihang Yu, Yuyin Zhou, Song Ba, Alan Yuille.

CVPR 2020. arXiv Version. Code

AdaBits: Neural Network Quantization with Adaptive Bit-Widths

Qing Jin*, Linjie Yang*, Zhenyu Liao

CVPR 2020. arXiv Version Code

AtomNAS: Fine-Grained End-to-End Neural Architecture Search

Jieru Mei, Yingwei Li, Xiaochen Lian, Xiaojie Jin, Linjie Yang, Alan Yuille, Jianchao Yang

ICLR 2020. Open Review. Code

Context-Aware Zero-Shot Recognition

Ruotian Luo, Ning Zhang, Bohyung Han, Linjie Yang

AAAI 2020. arXiv Version. Code


Video Instance Segmentation

Linjie Yang, Yuchen Fan, Ning Xu.

ICCV 2019. arXiv Version Code Dataset

Streamlined Dense Video Captioning

Jonghwan Mun, Linjie Yang, Zhou Ren, Ning Xu, Bohyung Han.

CVPR 2019 (Oral). arXiv Version

Slimmable Neural Networks.

Jiahui Yu, Linjie Yang, Ning Xu, Jianchao Yang, Thomas Huang.

ICLR 2019. OpenReview Code


Youtube-VOS: Sequence-to-Sequence Video Object Segmentation.

Ning Xu, Linjie Yang, Yuchen Fan, Jianchao Yang, Dingcheng Yue, Yuchen Liang, Brian Price, Scott Cohen, Thomas Huang.

ECCV 2018. arXiv Version Dataset

Efficient Video Object Segmentation via Network Modulation

Linjie Yang, Yanran Wang, Xuehan Xiong, Jianchao Yang, Aggelos K. Katsaggelos.

CVPR 2018. arXiv Version Code

Before 2018

Dense Captioning with Joint Inference and Visual Context.

Linjie Yang, Kevin Tang, Jianchao Yang, Li-Jia Li.

CVPR 2017. arXiv Version Code

A Large-Scale Car Dataset for Fine-Grained Categorization and Verification

Linjie Yang, Ping Luo, Chen Change Loy, Xiaoou Tang.

CVPR 2015. PDF Dataset extended work on arXiv Code

Depth from Water Reflection

Linjie Yang, Jianzhuang Liu, and Xiaoou Tang

IEEE Transactions on Image Processing, 24(4), 1235-1243. PDF

Object Detection and Viewpoint Estimation with Auto-masking Neural Network

Linjie Yang, Jianzhuang Liu, and Xiaoou Tang

ECCV 2014. PDF

Complex 3D General Object Reconstruction from Line Drawings

Linjie Yang, Jianzhuang Liu, and Xiaoou Tang

ICCV 2013. PDF

Invited Talks

"A Large-Scale Car Dataset for Fine-Grained Categorization and Verification", In 3rd Workshop on Vehicle Retrieval in Surveillance (VRS 2015), Karlsruhe, Germany, August 2015.

"Introduction to Neural Architecture Search for Computer Vision", In ECCV 2020 Tutorial on From HPO to NAS: Automated Deep Learning, August 2020.

Workshop Organizers

Large-Scale Video Object Segmentation Challenge in conjunction with ECCV 2018 / ICCV 2019 / CVPR 2021

Tutorial on From HPO to NAS: Automated Deep Learning in conjunction with ECCV 2020

Review Service



IEEE Transactions on Intelligent Transportation Systems

IEEE Transactions on Image Processing

Image and Vision Computing

WACV 2017, 2018

ACM Multimedia 2017

IJCAI 2017, 2018

CVPR 2018, 2019, 2020, 2021

ECCV 2018 2020

ICCV 2019

NeurIPS 2021