Revisiting the “Video” in Video-Language Understanding

Author:

Buch Shyamal1,Eyzaguirre Cristobal1,Gaidon Adrien2,Wu Jiajun1,Fei-Fei Li1,Niebles Juan Carlos1

Affiliation:

1. Stanford University

2. Toyota Research Institute

Funder

Toyota Research Institute

Samsung

Salesforce

Office of Naval Research

Publisher

IEEE

Reference62 articles.

1. Learning spatiotemporal representation with pseudo-3d residual networks;qiu;CVPR,2017

2. An information divergence measure between neural text and human text;pillutla;NeurIPS,2021

3. Metadata Normalization

4. Roberta: A robustly optimized bert pretraining approach;liu;ArXiv Preprint,2019

5. No frame left behind: Full Video Action Recognition

Cited by 41 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. Hardware-accelerated integrated optoelectronic platform towards real-time high-resolution hyperspectral video understanding;Nature Communications;2024-08-15

2. Short Video Ordering via Position Decoding and Successor Prediction;Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval;2024-07-10

3. Cascade transformers with dynamic attention for video question answering;Computer Vision and Image Understanding;2024-05

4. Multimodal AI-Based Summarization and Storytelling for Soccer on Social Media;Proceedings of the ACM Multimedia Systems Conference 2024 on ZZZ;2024-04-15

5. Multi-Granularity Contrastive Cross-Modal Collaborative Generation for End-to-End Long-Term Video Question Answering;IEEE Transactions on Image Processing;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