VidTr: Video Transformer Without Convolutions-Reference-Cited by-同舟云学术

登录注册会员服务联系我们

VidTr: Video Transformer Without Convolutions

Published:2021-10 Issue: Volume: Page:
ISSN:
Container-title:2021 IEEE/CVF International Conference on Computer Vision (ICCV)
language:
Short-container-title:

Author:

Zhang Yanyi¹,Li Xinyu¹,Liu Chunhui¹,Shuai Bing¹,Zhu Yi¹,Brattoli Biagio¹,Chen Hao¹,Marsic Ivan²,Tighe Joseph¹

Affiliation:

1. Amazon Web Service

2. Rutgers University

Publisher

IEEE

Link

http://xplorestaging.ieee.org/ielx7/9709627/9709628/09710952.pdf?arnumber=9710952

Reference65 articles.

1. TEINet: Towards an Efficient Architecture for Video Recognition

2. TEA: Temporal Excitation and Aggregation for Action Recognition

3. Directional temporal modeling for action recognition;li;European Conference on Computer Vision,2020

Cited by 132 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. SFormer: An end-to-end spatio-temporal transformer architecture for deepfake detection;Forensic Science International: Digital Investigation;2024-12

2. Spatio-temporal adaptive convolution and bidirectional motion difference fusion for video action recognition;Expert Systems with Applications;2024-12

3. CoSTA: Co-training spatial–temporal attention for blind video quality assessment;Expert Systems with Applications;2024-12

4. STMixer: A One-Stage Sparse Action Detector;IEEE Transactions on Pattern Analysis and Machine Intelligence;2024-10

5. How to Improve Video Analytics with Action Recognition: A Survey;ACM Computing Surveys;2024-08-08

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