Beyond Appearance: Multi-Frame Spatio-Temporal Context Memory Networks for Efficient and Robust Video Object Segmentation-Reference-Cited by-同舟云学术

登录注册会员服务联系我们

Beyond Appearance: Multi-Frame Spatio-Temporal Context Memory Networks for Efficient and Robust Video Object Segmentation

Published:2024 Issue: Volume:33 Page:4853-4866
ISSN:1057-7149
Container-title:IEEE Transactions on Image Processing
language:
Short-container-title:IEEE Trans. on Image Process.

Author:

Dang Jisheng¹^ORCID,Zheng Huicheng¹^ORCID,Xu Xiaohao²^ORCID,Wang Longguang³^ORCID,Guo Yulan⁴^ORCID

Affiliation:

1. School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China

2. Robotics Institute, University of Michigan, Ann Arbor, MI, USA

3. School of Electronic Science and Technology, Air Force Aviation University, Changchun, China

4. School of Electronics and Communication Engineering, Sun Yat-sen University, Shenzhen Campus, Shenzhen, China

Funder

National Natural Science Foundation of China

Guangdong Basic and Applied Basic Research Foundation

Shenzhen Science and Technology Program

Publisher

Institute of Electrical and Electronics Engineers (IEEE)

Link

http://xplorestaging.ieee.org/ielx8/83/10346232/10659365.pdf?arnumber=10659365

Reference77 articles.

1. Rethinking space-time networks with improved memory coverage for efficient video object segmentation;Cheng

2. Online Learning-Based Multi-Stage Complexity Control for Live Video Coding

3. A Spatial-Temporal Recurrent Neural Network for Video Saliency Prediction

4. SPADE-E2VID: Spatially-Adaptive Denormalization for Event-Based Video Reconstruction

5. HRSiam: High-Resolution Siamese Network, Towards Space-Borne Satellite Video Tracking

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