LexLIP: Lexicon-Bottlenecked Language-Image Pre-Training for Large-Scale Image-Text Sparse Retrieval

Author:

Luo Ziyang1,Zhao Pu2,Xu Can2,Geng Xiubo2,Shen Tao2,Tao Chongyang2,Ma Jing1,Lin Qingwei2,Jiang Daxin2

Affiliation:

1. Hong Kong Baptist University,Hong Kong SAR,China

2. Microsoft Corporation

Funder

National Natural Science Foundation of China

Publisher

IEEE

Reference55 articles.

1. Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval

2. Beit: BERT pre-training of image transformers;Bao

3. Globally trained handwritten word recognizer using spatial representation, convolutional neural networks, and hidden markov models;Bengio

4. Food-101 – Mining Discriminative Components with Random Forests

5. Off the Beaten Path

Cited by 4 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. Hypergraph clustering based multi-label cross-modal retrieval;Journal of Visual Communication and Image Representation;2024-08

2. Object search by a concept-conditioned object detector;Neural Computing and Applications;2024-05-20

3. Semantic Completion: Enhancing Image-Text Retrieval with Information Extraction and Compression;Lecture Notes in Computer Science;2024

4. Efficient Image-Text Retrieval via Keyword-Guided Pre-Screening;IEEE Transactions on Circuits and Systems for Video Technology;2023

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