X-CLIP: End-to-End Multi-grained Contrastive Learning for Video-Text Retrieval

Author:

Ma Yiwei1,Xu Guohai2,Sun Xiaoshuai1,Yan Ming2,Zhang Ji2,Ji Rongrong1

Affiliation:

1. Xiamen University, Xiamen, China

2. Alibaba Group, Hangzhou, China

Funder

the National Natural Science Foundation of China

the Natural Science Foundation of Fujian Province of China

Guangdong Basic and Applied Basic Research Foundatio

the National Science Fund for Distinguished Young Scholars

Publisher

ACM

Reference66 articles.

1. Elad Amrani , Rami Ben-Ari , Daniel Rotman , and Alex Bronstein . 2020. Noise estimation using density estimation for self-supervised multimodal learning. arXiv preprint arXiv:2003.03186 8 ( 2020 ). Elad Amrani, Rami Ben-Ari, Daniel Rotman, and Alex Bronstein. 2020. Noise estimation using density estimation for self-supervised multimodal learning. arXiv preprint arXiv:2003.03186 8 (2020).

2. Localizing Moments in Video with Natural Language

3. Anurag Arnab , Mostafa Dehghani , Georg Heigold , Chen Sun , Mario Lucic , and Cordelia Schmid . 2021 . Vivit: A video vision transformer. arXiv preprint arXiv:2103.15691 (2021). Anurag Arnab, Mostafa Dehghani, Georg Heigold, Chen Sun, Mario Lucic, and Cordelia Schmid. 2021. Vivit: A video vision transformer. arXiv preprint arXiv:2103.15691 (2021).

4. Max Bain , Arsha Nagrani , Gül Varol , and Andrew Zisserman . 2021. Frozen in time: A joint video and image encoder for end-to-end retrieval. arXiv preprint arXiv:2104.00650 ( 2021 ). Max Bain, Arsha Nagrani, Gül Varol, and Andrew Zisserman. 2021. Frozen in time: A joint video and image encoder for end-to-end retrieval. arXiv preprint arXiv:2104.00650 (2021).

5. Gedas Bertasius , Heng Wang , and Lorenzo Torresani . 2021. Is Space-Time At- tention All You Need for Video Understanding? arXiv preprint arXiv:2102.05095 ( 2021 ). Gedas Bertasius, Heng Wang, and Lorenzo Torresani. 2021. Is Space-Time At- tention All You Need for Video Understanding? arXiv preprint arXiv:2102.05095 (2021).

Cited by 65 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

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