LayoutLM: Pre-training of Text and Layout for Document Image Understanding
Yiheng Xu1∗, Minghao Li2, Lei Cui3, Shaohan Huang3, Furu Wei3, Ming Zhou3
1Harbin Institute of Techno……继续阅读 »
scott
3天前 7浏览 0评论
0个赞
Does Object Recognition Work for Everyone?
Terrance DeVries
Ishan Misra11footnotemark: 1
Changhan Wang11footnotemark: 1
Laurens van der Maaten
Facebook AI Research
{tldev……继续阅读 »
scott
5天前 9浏览 0评论
0个赞
Breaking the cycle—Colleagues are all you need
Ori Nizan
Technion, Israel
snizori@campus.technion.ac.il
Ayellet Tal
Technion, Israel
ayellet@ee.technion.ac.il
Abstract
Th……继续阅读 »
scott
5天前 9浏览 0评论
0个赞
Adversarial Domain Adaptation with Domain Mixup
Minghao Xu,1
Jian Zhang,1
Bingbing Ni,1,21
Teng Li,3
Chengjie Wang,4
Qi Tian,5
Wenjun Zhang1
1Shanghai Jiao Tong University, Ch……继续阅读 »
scott
5天前 8浏览 0评论
0个赞
Folding-based compression of point cloud attributes
Abstract
Existing techniques to compress point cloud attributes leverage either geometric or video-based compression tools.……继续阅读 »
scott
5天前 10浏览 0评论
0个赞
Attention Is All You Need
/ANDAshish Vaswani
Google Brain
avaswani@google.com
&Noam Shazeer11footnotemark: 1
Google Brain
noam@google.com
&Niki Parmar11footnotemark: 1
……继续阅读 »
scott
6天前 8浏览 0评论
0个赞
Joint Discriminative and Generative Learning for Person Re-identification
Zhedong Zheng1,2 Xiaodong Yang1 Zhiding Yu1
Liang Zheng3 Yi Yang2 Jan Kautz1
1NVIDIA 2CAI, U……继续阅读 »
scott
6天前 8浏览 0评论
0个赞
CutMix: Regularization Strategy to Train Strong Classifiers
with Localizable Features
Sangdoo Yun1 Dongyoon Han1 ……继续阅读 »
scott
6天前 8浏览 0评论
0个赞
ActiveMoCap: Optimized Drone Flight for Active Human Motion Capture
Sena Kiciroglu
CVLAB, EPFL, Lausanne
Helge Rhodin
Sudipta Sinha
Microsoft Research, Redmond
Mathieu ……继续阅读 »
scott
6天前 6浏览 0评论
0个赞
DeepMOT: A Differentiable Framework for Training Multiple Object Trackers
Yihong Xu
Yutong Ban
Xavier Alameda-Pineda
Radu Horaud
Inria
Grenoble Rhone-Alpes, France
{firstn……继续阅读 »
scott
1周前 (06-23) 10浏览 0评论
0个赞
