Cross-Modal Retrieval With Partially Mismatched Pairs

Author:

Hu Peng1ORCID,Huang Zhenyu1ORCID,Peng Dezhong1ORCID,Wang Xu1ORCID,Peng Xi1ORCID

Affiliation:

1. College of Computer Science, Sichuan University, Chengdu, China

Funder

National Key R&D Program of China

National Natural Science Foundation of China

Sichuan Science and Technology Planning Project

China Postdoctoral Science Foundation

Open Research Projects of Zhejiang Lab

Fundamental Research Funds for the Central Universities

Publisher

Institute of Electrical and Electronics Engineers (IEEE)

Subject

Applied Mathematics,Artificial Intelligence,Computational Theory and Mathematics,Computer Vision and Pattern Recognition,Software

Reference53 articles.

1. Co-teaching: Robust training of deep neural networks with extremely noisy labels;han;Proc Int Conf Neural Inf Process,2018

2. Masking: A new perspective of noisy supervision;han;Proc Int Conf Neural Inf Process,2018

3. Robust early-learning: Hindering the memorization of noisy labels;xia;Proc Int Conf Learn Representations,2020

4. How does disagreement help generalization against label corruption?;yu;Proc Int Conf Mach Learn,2019

5. Learning Fragment Self-Attention Embeddings for Image-Text Matching

Cited by 23 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. Parallel weight control based on policy gradient of relation refinement for cross-modal retrieval;Engineering Applications of Artificial Intelligence;2024-10

2. Fast unsupervised multi-modal hashing based on piecewise learning;Knowledge-Based Systems;2024-09

3. Breaking Through the Noisy Correspondence: A Robust Model for Image-Text Matching;ACM Transactions on Information Systems;2024-08-19

4. UGNCL: Uncertainty-Guided Noisy Correspondence Learning for Efficient Cross-Modal Matching;Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval;2024-07-10

5. Semantic Information Reasoning and Multi-Step Cross-Modal Interaction Network for Image-Text Retrieval;2024 International Joint Conference on Neural Networks (IJCNN);2024-06-30

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