登录 注册 会员服务 联系我们

Zero Experience Required: Plug & Play Modular Transfer Learning for Semantic Visual Navigation

  • Published:2022-06 Issue: Volume: Page:
  • ISSN:
  • Container-title:2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
  • language:
  • Short-container-title:

Author:

Al-Halah Ziad1,Ramakrishnan Santhosh K.1,Grauman Kristen1

Affiliation:

1. The University of Texas at Austin

Funder

DARPA

Publisher

IEEE

Reference75 articles.

1. Taskonomy: Disentangling Task Transfer Learning

2. Learning to see before learning to act: Visual pre-training for manipulation;lin;ICRA,2020

3. Auxiliary Tasks and Exploration Enable ObjectGoal Navi-gation;ye;ICCV,2021

4. Visual semantic navigation using scene priors;yang;ICLRE,2019

5. Does computer vision matter for action?

Cited by 17 articles. 订阅此论文施引文献 订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. Toward Learning-Based Visuomotor Navigation With Neural Radiance Fields;IEEE Transactions on Industrial Informatics;2024-06

2. What Do We Learn from a Large-Scale Study of Pre-Trained Visual Representations in Sim and Real Environments?;2024 IEEE International Conference on Robotics and Automation (ICRA);2024-05-13

3. Exploitation-Guided Exploration for Semantic Embodied Navigation;2024 IEEE International Conference on Robotics and Automation (ICRA);2024-05-13

4. MVSSC: Meta-reinforcement learning based visual indoor navigation using multi-view semantic spatial context;Pattern Recognition Letters;2024-01

5. A Survey of Object Goal Navigation;IEEE Transactions on Automation Science and Engineering;2024
同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线，采集、加工和组织学术论文而形成的新型学术文献查询和分析系统，可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容，当前同舟云学术共收录了国内外主流学术期刊6万余种，收集的期刊论文及会议论文总量共计约1.5亿篇，并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询！咨询电话：010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3