Correspondence Autoencoders for Cross-Modal Retrieval

Author:

Feng Fangxiang1,Wang Xiaojie1,Li Ruifan1,Ahmad Ibrar2

Affiliation:

1. Beijing University of Posts and Telecommunications, Beijing, China

2. Beijing University of Posts and Telecommunications and University of Peshawar, Pakistan

Abstract

This article considers the problem of cross-modal retrieval, such as using a text query to search for images and vice-versa. Based on different autoencoders, several novel models are proposed here for solving this problem. These models are constructed by correlating hidden representations of a pair of autoencoders. A novel optimal objective, which minimizes a linear combination of the representation learning errors for each modality and the correlation learning error between hidden representations of two modalities, is used to train the model as a whole. Minimizing the correlation learning error forces the model to learn hidden representations with only common information in different modalities, while minimizing the representation learning error makes hidden representations good enough to reconstruct inputs of each modality. To balance the two kind of errors induced by representation learning and correlation learning, we set a specific parameter in our models. Furthermore, according to the modalities the models attempt to reconstruct they are divided into two groups. One group including three models is named multimodal reconstruction correspondence autoencoder since it reconstructs both modalities. The other group including two models is named unimodal reconstruction correspondence autoencoder since it reconstructs a single modality. The proposed models are evaluated on three publicly available datasets. And our experiments demonstrate that our proposed correspondence autoencoders perform significantly better than three canonical correlation analysis based models and two popular multimodal deep models on cross-modal retrieval tasks.

Funder

National High Technology Research and Development Program of China

discipline building plan in 111 base

Fundamental Research Funds for the Central Universities

National Natural Science Foundation of China

Publisher

Association for Computing Machinery (ACM)

Subject

Computer Networks and Communications,Hardware and Architecture

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. Dual-Pathway Deep Hashing-Based Adversarial Learning for Cross-Modal Retrieval;International Journal of Pattern Recognition and Artificial Intelligence;2024-06-29

2. Fabric image retrieval based on multi-modal feature fusion;Signal, Image and Video Processing;2024-01-19

3. Learning binary codes for fast image retrieval with sparse discriminant analysis and deep autoencoders;Intelligent Data Analysis;2023-05-18

4. Coordinated and specific autoencoder for cross-modal retrieval;International Conference on Mechanisms and Robotics (ICMAR 2022);2022-11-10

5. Self-Lifting: A Novel Framework for Unsupervised Voice-Face Association Learning;Proceedings of the 2022 International Conference on Multimedia Retrieval;2022-06-27

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