Deep Enhanced-Similarity Attention Cross-modal Hashing Learning
Open Access
- 12 June 2023
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 612-616
Abstract
Despite the great success of existing cross-modal retrieval methods, existing unsupervised cross-modal hashing methods still suffer from common problems. First, the features extracted from the text are too sparse. Second, the similarity matrices of each different modality cannot be fused adaptively. In this paper, we propose Deep Enhanced-Similarity Attention Hashing (DESAH) to alleviate the above problems. Firstly, we construct a text encoder expanding graph convolutional neural network to simultaneously extract features of samples and their semantic neighbors to enrich text features. Secondly, we propose an enhanced attention fusion mechanism. The mechanism is used to adaptively fuse the similarity matrices within different modalities to form a unified inter-modal similarity matrix to guide the learning of hash functions. Extensive experiments have demonstrated that DESAH provides significant improvements in cross-modal retrieval tasks compared to baseline methods.Keywords
Funding Information
- Chongqing Natural Science Foundation of China (CSTB2022NSCQ-MSX1417)
- Science and Technology Research Program of Chongqing Municipal Education Commission (KJZD-K202200513)
This publication has 13 references indexed in Scilit:
- Joint and individual matrix factorization hashing for large-scale cross-modal retrievalPattern Recognition, 2020
- Deep Semantic-Alignment Hashing for Unsupervised Cross-Modal Retrieval2020
- Label-Based Deep Semantic Hashing for Cross-Modal Retrieval2019
- Deep Joint-Semantics Reconstructing Hashing for Large-Scale Unsupervised Cross-Modal Retrieval2019
- Multi-Pathway Generative Adversarial Hashing for Unsupervised Cross-Modal RetrievalIEEE Transactions on Multimedia, 2019
- Deep Binary Reconstruction for Cross-Modal HashingIEEE Transactions on Multimedia, 2018
- Self-Supervised Adversarial Hashing Networks for Cross-Modal Retrieval2018
- Microsoft COCO: Common Objects in Context2014
- NUS-WIDE2009
- The MIR flickr retrieval evaluation2008