Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Fanyi Xiao

YolactEdge: Real-time Instance Segmentation on the Edge (Jetson AGX Xavier: 30 FPS, RTX 2080 Ti: 170 FPS)


Dec 22, 2020
Haotian Liu, Rafael A. Rivera Soto, Fanyi Xiao, Yong Jae Lee

* This work has been submitted to the IEEE for possible publication. Copyright may be transferred without notice, after which this version may no longer be accessible 

  Access Paper or Ask Questions

MARS: Mixed Virtual and Real Wearable Sensors for Human Activity Recognition with Multi-Domain Deep Learning Model


Oct 09, 2020
Ling Pei, Songpengcheng Xia, Lei Chu, Fanyi Xiao, Qi Wu, Wenxian Yu, Robert Qiu


  Access Paper or Ask Questions

Delving Deeper into Anti-aliasing in ConvNets


Aug 21, 2020
Xueyan Zou, Fanyi Xiao, Zhiding Yu, Yong Jae Lee

* [Accepted in BMVC2020] code: https://maureenzou.github.io/ddac/ 

  Access Paper or Ask Questions

A Deep Learning Method for Complex Human Activity Recognition Using Virtual Wearable Sensors


Mar 06, 2020
Fanyi Xiao, Ling Pei, Lei Chu, Danping Zou, Wenxian Yu, Yifan Zhu, Tao Li


  Access Paper or Ask Questions

Audiovisual SlowFast Networks for Video Recognition


Jan 23, 2020
Fanyi Xiao, Yong Jae Lee, Kristen Grauman, Jitendra Malik, Christoph Feichtenhofer

* Technical report 

  Access Paper or Ask Questions

YOLACT++: Better Real-time Instance Segmentation


Dec 03, 2019
Daniel Bolya, Chong Zhou, Fanyi Xiao, Yong Jae Lee

* Journal extension of our previous conference paper arXiv:1904.02689 

  Access Paper or Ask Questions

STEP: Spatio-Temporal Progressive Learning for Video Action Detection


Apr 19, 2019
Xitong Yang, Xiaodong Yang, Ming-Yu Liu, Fanyi Xiao, Larry Davis, Jan Kautz

* CVPR 2019 (Oral) 

  Access Paper or Ask Questions

YOLACT: Real-time Instance Segmentation


Apr 04, 2019
Daniel Bolya, Chong Zhou, Fanyi Xiao, Yong Jae Lee


  Access Paper or Ask Questions

Video Object Detection with an Aligned Spatial-Temporal Memory


Jul 27, 2018
Fanyi Xiao, Yong Jae Lee


  Access Paper or Ask Questions

Who Will Share My Image? Predicting the Content Diffusion Path in Online Social Networks


Nov 29, 2017
Wenjian Hu, Krishna Kumar Singh, Fanyi Xiao, Jinyoung Han, Chen-Nee Chuah, Yong Jae Lee

* 9 pages, 6 figures 

  Access Paper or Ask Questions

Weakly-supervised Visual Grounding of Phrases with Linguistic Structures


May 03, 2017
Fanyi Xiao, Leonid Sigal, Yong Jae Lee

* CVPR 2017 

  Access Paper or Ask Questions

Track and Transfer: Watching Videos to Simulate Strong Human Supervision for Weakly-Supervised Object Detection


Apr 19, 2016
Krishna Kumar Singh, Fanyi Xiao, Yong Jae Lee

* IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016 

  Access Paper or Ask Questions

Multi-Task Regularization with Covariance Dictionary for Linear Classifiers


Oct 21, 2013
Fanyi Xiao, Ruikun Luo, Zhiding Yu


  Access Paper or Ask Questions