Fast Unsupervised Cross-Modal Hashing with Robust Factorization and Dual Projection
Open Access
- 26 November 2024
- journal article
- research article
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Multimedia Computing, Communications, and Applications
- Vol. 20 (12) , 1-21
Abstract
Unsupervised hashing has attracted extensive attention in effectively and efficiently tackling large-scale cross-modal retrieval task. Existing methods typically try to mine the latent common subspace across multimodal data without any category annotation. Despite the exciting progress, there are still three challenges that need to be further addressed: (1) efficiently improving the robustness during latent common subspace learning; (2) harmoniously embedding the intra-modal inherence and inter-modal relevance of multimodal data into Hamming space; and (3) effectively reducing the training time complexity and making the model scalable for large-scale datasets. To well address the above challenges, this study proposes a method named Fast Unsupervised Cross-Modal Hashing (FUCH). Specifically, FUCH proposes a semantic-aware collective matrix factorization to learn robust representation via exploiting latent category-specific attributes, and introduces Cauchy loss to measure the factorization process. Accordingly, the above process can effectively embed potential discriminative information into common space, while making the model insensitive for outliers. Moreover, FUCH designs a dual projection learning scheme, which not only learns modality-unique hash functions to excavate individual properties but also learns modality-mutual hash functions to multimodal correlational properties. Experimental results on three benchmark datasets verify the effectiveness of FUCH under various scenarios.Keywords
Funding Information
- National Natural Science Foundation of China (U23A20389, 62176141, 62176139, 62206160)
- Shandong Provincial Natural Science Foundation (ZR2022QF082)
- Major Basic Research Project of Natural Science Foundation of Shandong Province (ZR2021ZD15)
- Taishan Scholar Project of Shandong Province (tsqn202103088)
- Shandong Provincial Natural Science Foundation for Distinguished Young Scholars (ZR2021JQ26)
- Major Science and Technology Innovation Project of Shandong Province (2021CXGC011204)
This publication has 53 references indexed in Scilit:
- High-order nonlocal Hashing for unsupervised cross-modal retrievalWorld Wide Web, 2021
- Joint and individual matrix factorization hashing for large-scale cross-modal retrievalPattern Recognition, 2020
- Modality-specific and shared generative adversarial network for cross-modal retrievalPattern Recognition, 2020
- Unsupervised Deep Cross-modal Hashing with Virtual Label RegressionNeurocomputing, 2020
- SCRATCH: A Scalable Discrete Matrix Factorization Hashing Framework for Cross-Modal RetrievalIEEE Transactions on Circuits and Systems for Video Technology, 2019
- Cross-Modal Discrete HashingPattern Recognition, 2018
- Robust and Flexible Discrete Hashing for Cross-Modal Similarity SearchIEEE Transactions on Circuits and Systems for Video Technology, 2017
- An Overview of Cross-Media Retrieval: Concepts, Methodologies, Benchmarks, and ChallengesIEEE Transactions on Circuits and Systems for Video Technology, 2017
- Semi-Paired Discrete Hashing: Learning Latent Hash Codes for Semi-Paired Cross-View RetrievalIEEE Transactions on Cybernetics, 2016
- Robust Cross-view Hashing for Multimedia RetrievalIEEE Signal Processing Letters, 2016