ViSTA: Vision and Scene Text Aggregation for Cross-Modal Retrieval
Author:
Affiliation:
1. School of Electronic and Computer Engineering, Peking University
2. Baidu Inc.,Department of Computer Vision Technology (VIS)
3. Peng Cheng Laboratory
Publisher
IEEE
Link
http://xplorestaging.ieee.org/ielx7/9878378/9878366/09880270.pdf?arnumber=9880270
Reference50 articles.
1. Textcaps: A dataset for image captioning with reading comprehension;sidorov;ECCV (2) volume 12347 of Lecture Notes in Computer Science,0
2. Conceptual Captions: A Cleaned, Hypernymed, Image Alt-text Dataset For Automatic Image Captioning
3. Efficient estimation of word representations in vector space;mikolov;ICLR (Workshop Poster),0
4. Thinking Fast and Slow: Efficient Text-to-Visual Retrieval with Transformers
5. StacMR: Scene-Text Aware Cross-Modal Retrieval
Cited by 43 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. A large cross-modal video retrieval dataset with reading comprehension;Pattern Recognition;2025-01
2. BagFormer: Better cross-modal retrieval via bag-wise interaction;Engineering Applications of Artificial Intelligence;2024-10
3. Video and audio are images: A cross-modal mixer for original data on video–audio retrieval;Knowledge-Based Systems;2024-09
4. bjEnet: a fast and accurate software bug localization method in natural language semantic space;Software Quality Journal;2024-07-22
5. MGN-Net: Multigranularity Graph Fusion Network in Multimodal for Scene Text Spotting;IEEE Internet of Things Journal;2024-07-15
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