Zobrazeno 1 - 9
of 9
pro vyhledávání: '"Xia Ye"'
Autor:
Jia, Chao, Yang, Yinfei, Xia, Ye, Chen, Yi-Ting, Parekh, Zarana, Pham, Hieu, Le, Quoc V., Sung, Yunhsuan, Li, Zhen, Duerig, Tom
Publikováno v:
International Conference on Machine Learning 2021
Pre-trained representations are becoming crucial for many NLP and perception tasks. While representation learning in NLP has transitioned to training on raw text without human annotations, visual and vision-language representations still rely heavily
Externí odkaz:
http://arxiv.org/abs/2102.05918
Autor:
Xia, Ye, Lee, Gwendolyn
We outline a contact-tracing strategy based on proximity sensing using mobile devices. We discuss what an ideal system should look like and what it can do. We show that, when adopted sufficiently broadly, such a contact-tracing strategy can bring COV
Externí odkaz:
http://arxiv.org/abs/2004.12576
Inspired by human vision, we propose a new periphery-fovea multi-resolution driving model that predicts vehicle speed from dash camera videos. The peripheral vision module of the model processes the full video frames in low resolution. Its foveal vis
Externí odkaz:
http://arxiv.org/abs/1903.09950
Autor:
Zheng, Xiaoying, Xia, Ye
One of the important problems for datacenter resource management is to place virtual machines (VMs) to physical machines (PMs) such that certain cost, profit or performance objective is optimized, subject to various constraints. In this paper, we con
Externí odkaz:
http://arxiv.org/abs/1903.02139
We study a difficult problem of how to schedule complex workflows with precedence constraints under a limited budget in the cloud environment. We first formulate the scheduling problem as an integer programming problem, which can be optimized and use
Externí odkaz:
http://arxiv.org/abs/1903.01154
Robust driver attention prediction for critical situations is a challenging computer vision problem, yet essential for autonomous driving. Because critical driving moments are so rare, collecting enough data for these situations is difficult with the
Externí odkaz:
http://arxiv.org/abs/1711.06406
In traditional massive content distribution with multiple sessions, the sessions form separate overlay networks and operate independently, where some sessions may suffer from insufficient resources even though other sessions have excessive resources.
Externí odkaz:
http://arxiv.org/abs/1307.2984
The paper investigates theoretical issues in applying the universal swarming technique to efficient content distribution. In a swarming session, a file is distributed to all the receivers by having all the nodes in the session exchange file chunks. B
Externí odkaz:
http://arxiv.org/abs/1306.0334
Efficient link scheduling in a wireless network is challenging. Typical optimal algorithms require solving an NP-hard sub-problem. To meet the challenge, one stream of research focuses on finding simpler sub-optimal algorithms that have low complexit
Externí odkaz:
http://arxiv.org/abs/1107.3199