SeiT: Storage-Efficient Vision Training with Tokens Using 1% of Pixel Storage-Reference-Cited by-同舟云学术

登录注册会员服务联系我们

SeiT: Storage-Efficient Vision Training with Tokens Using 1% of Pixel Storage

Published:2023-10-01 Issue: Volume:33 Page:17202-17213
ISSN:
Container-title:2023 IEEE/CVF International Conference on Computer Vision (ICCV)
language:
Short-container-title:

Author:

Park Song¹,Chun Sanghyuk¹,Heo Byeongho¹,Kim Wonjae¹,Yun Sangdoo¹

Affiliation:

1. NAVER AI Lab

Publisher

IEEE

Link

http://xplorestaging.ieee.org/ielx7/10376473/10376477/10376571.pdf?arnumber=10376571

Reference78 articles.

1. Youtube-8m: A large-scale video classification benchmark;Abu-El-Haija,2016

2. Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering

3. VQA: Visual Question Answering

4. Testimages: a large-scale archive for testing visual devices and basic image processing algorithms;Asuni;STAG,2014

5. Obfuscated gradients give a false sense of security: Circumventing defenses to adversarial examples;Athalye

Cited by 1 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. Towards Practical and Efficient Image-to-Speech Captioning with Vision-Language Pre-Training and Multi-Modal Tokens;ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP);2024-04-14

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