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 3rd Large-scale Video Object Segmentation Challenge in conjunction with CVPR 2021. We have three tracks this year: video object segmentation, video instance segmentation and the branch new language referring video segmentation. Call for participants!
  • Two papers accepted by AAAI 2021.
  • Code for our recent papers "AdaBits" and "Scale-Adjusted Training" on network quantization are released!
  • I am co-organizing ECCV 2020 tutorial on From HPO to NAS: Automated Deep Learning. For details, checkout our website.
  • One paper accepted by BMVC 2020.
  • Two papers accepted by CVPR 2020.
  • Our paper "AtomNAS: Fine-Grained End-to-End Neural Architecture Search" is accepted by ICLR 2020.
  • Our paper "Context-Aware Zero-Shot Recognition" is accepted by AAAI 2020.
  • One paper about a new task "Video Instance Segmentation" accepted by ICCV 2019. It is also the task in one track of our 2nd Large-scale Video Object Segmentation Challenge
  • We are organizing the 2nd Large-scale Video Object Segmentation Challenge in conjunction with ICCV 2019. See details on challenge website!
  • Our paper on dense video captioning is accepted by CVPR 2019 as oral presentation.
  • Our paper "Slimmable Neural Networks" is accepted by ICLR 2019.

Publications

2021
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

2020
Neural Network Quantization with Scale-Adjusted Training
Qing Jin, Linjie Yang, Zhenyu Liao, Xiaoning Qian

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 ReviewCode

Context-Aware Zero-Shot Recognition
Ruotian Luo, Ning Zhang, Bohyung Han, Linjie Yang
AAAI 2020. arXiv Version. Code

2019
Video Instance Segmentation
Linjie Yang, Yuchen Fan, Ning Xu.

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

2018
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. 

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

Review Service

TPAMI
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  
ECCV 2018 2020
ICCV 2019

Contact

yljatthu@gmail.com
Linkedin