欢迎,计算机科学与信息计算爱好者!

标签:research

LayoutLM: Pre-training of Text and Layout for Document Image Understanding

LayoutLM: Pre-training of Text and Layout for Document Image Understanding Yiheng Xu1∗, Minghao Li2, Lei Cui3, Shaohan Huang3, Furu Wei3, Ming Zhou31Harbin Institute of Te……

Does Object Recognition Work for Everyone?

Does Object Recognition Work for Everyone? Terrance DeVries   Ishan Misra11footnotemark: 1   Changhan Wang11footnotemark: 1   Laurens van der Maaten……

Breaking the cycle—Colleagues are all you need

Breaking the cycle—Colleagues are all you need Ori NizanTechnion, Israelsnizori@campus.technion.ac.il   Ayellet TalTechnion, Israelayellet@ee.technion.ac.il Abs……

Adversarial Domain Adaptation with Domain Mixup

Adversarial Domain Adaptation with Domain Mixup Minghao Xu,1 Jian Zhang,1 Bingbing Ni,1,21 Teng Li,3Chengjie Wang,4 Qi Tian,5 Wenjun Zhang11Shanghai Jiao Tong University, China,……

Folding-based compression of point cloud attributes

Folding-based compression of point cloud attributes Abstract Existing techniques to compress point cloud attributes leverage either geometric or video-based compression tools. ……

Attention Is All You Need

Attention Is All You Need /ANDAshish VaswaniGoogle Brainavaswani@google.com&Noam Shazeer11footnotemark: 1Google Brainnoam@google.com&Niki Parmar11footnotemark: 1Google Res……

Joint Discriminative and Generative Learning for Person Re-identification

Joint Discriminative and Generative Learning for Person Re-identification Zhedong Zheng1,2  Xiaodong Yang1  Zhiding Yu1Liang Zheng3  Yi Yang2  Jan Kautz11NVID……

CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features

CutMix: Regularization Strategy to Train Strong Classifierswith Localizable Features Sangdoo Yun1        Dongyoon Han1   &n……

ActiveMoCap: Optimized Drone Flight for Active Human Motion Capture

ActiveMoCap: Optimized Drone Flight for Active Human Motion Capture Sena KicirogluCVLAB, EPFL, LausanneHelge RhodinSudipta SinhaMicrosoft Research, RedmondMathieu SalzmannCVLAB, ……

DeepMOT: A Differentiable Framework for Training Multiple Object Trackers

DeepMOT: A Differentiable Framework for Training Multiple Object Trackers Yihong Xu   Yutong Ban   Xavier Alameda-Pineda   Radu HoraudInriaGrenoble R……