Journal
NEUROCOMPUTING
Volume 331, Issue -, Pages 165-175Publisher
ELSEVIER
DOI: 10.1016/j.neucom.2018.11.042
Keywords
Cross-modal retrieval; Multi-modal data; Autoencoder
Categories
Funding
- National Natural Science Foundation of China [61672497, 61332016, 61620106009, 61650202, U1636214]
- National Basic Research Program of China (973 Program) [2015CB351802]
- Key Research Program of Frontier Sciences of CAS [QYZDJ-SSW-SYS013]
Ask authors/readers for more resources
Cross-modal retrieval has gained much attention in recent years. As the research mainstream, most of existing approaches learn projections for data from different modalities into a common space where data can be compared directly. However, they neglect the preservation of feature and semantic information, so they are unable to obtain satisfactory results as expected. In this paper, we propose a two-stage learning method to learn multi-modal mappings that project multi-modal data to low dimensional embeddings that preserve both feature and semantic information. In the first stage, we combine both low-level feature and high-level semantic information to learn feature-aware semantic code vectors. In the second stage, we use encoder-decoder paradigm to learn projections. The encoder projects feature vectors to code vectors, and the decoder projects code vectors back to feature vectors. The encoder-decoder paradigm guarantees the embeddings to preserve both feature and semantic information. An alternating minimization procedure is developed to solve the multi-modal semantic autoencoder optimization problem. Extensive experiments on three benchmark datasets demonstrate that the proposed method outperforms state-of-the-art cross-modal retrieval methods. (C) 2018 Elsevier B.V. All rights reserved.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available