Broaden Your Views for Self-Supervised Video Learning

Author:

Recasens Adria1,Luc Pauline1,Alayrac Jean-Baptiste1,Wang Luyu1,Strub Florian1,Tallec Corentin1,Malinowski Mateusz1,Patraaucean Viorica1,Altche Florent1,Valko Michal1,Grill Jean-Bastien1,van den Oord Aaron1,Zisserman Andrew1

Affiliation:

1. DeepMind

Publisher

IEEE

Reference89 articles.

1. UCF101: A dataset of 101 human actions classes from videos in the wild;soomro,2012

2. Two-stream convo-lutional networks for action recognition in videos;simonyan;ICLRE,2014

3. Visual Grounding in Video for Unsupervised Word Translation

4. Learning to Localize Sound Source in Visual Scenes

5. VideoBERT: A Joint Model for Video and Language Representation Learning

Cited by 48 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. Video Foundation Models for Animal Behavior Analysis;2024-07-31

2. Self-supervised learning for interventional image analytics: toward robust device trackers;Journal of Medical Imaging;2024-05-15

3. Audio-visual saliency prediction with multisensory perception and integration;Image and Vision Computing;2024-03

4. How Does Contrastive Learning Organize Images?;2024 IEEE/CVF Winter Conference on Applications of Computer Vision Workshops (WACVW);2024-01-01

5. COMEDIAN: Self-Supervised Learning and Knowledge Distillation for Action Spotting Using Transformers;2024 IEEE/CVF Winter Conference on Applications of Computer Vision Workshops (WACVW);2024-01-01

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