Author:
Shang Fei, ,Zhang Huaxiang,Sun Jiande,Liu Li,Zeng Hui
Abstract
Unlike traditional methods that directly map different modalities into an isomorphic subspace for cross-media retrieval, this paper proposes a cross-media retrieval algorithm based on the consistency of collaborative representation (called CR-CMR). In order to measure the similarity between data coming from different modalities, CR-CMR first takes the advantage of dictionary learning techniques to obtain homogeneous collaborative representation for texts and images, then, it considers the semantic consistency of different modalities simultaneously and maps the collaborative representation coefficients into an isomorphic semantic subspace to conduct cross-media retrieval. Experimental results on three state-of-the-art datasets show that the algorithm is effective.
Publisher
Fuji Technology Press Ltd.
Subject
Artificial Intelligence,Computer Vision and Pattern Recognition,Human-Computer Interaction
Reference36 articles.
1. M. Zhao, H. Zhang, and L. Meng, “An Angle Structure Descriptor for Image retrieval,” China Communications, Vol.13, No.8, pp. 222-230, 2016.
2. J. Sun, X. Liu, W. Wan, J. Li, D. Zhao, and H. Zhang, “Video Hashing Based on Appearance and Attention Features Fusion via DBN,” Neurocomputing, Vol.213, pp. 84-94, 2016.
3. H. Zhang and J. Weng, “Measuring Multi-modality Similarities Via Subspace Learning for Cross-Media Retrieval,” Pacific-Rim Conf. on Multimedia, pp. 979-988, 2006.
4. H. Zhang, F. Wu, and Y. Zhuang,“Cross-Media Retrieval Method Based on Feature Subspace Learning,” Pattern Recognition and Artificial Intelligence, Vol.21, No.6, pp. 739-745, 2008.
5. D. Mandal and S. Biswas, “Generalized Coupled Dictionary Learning Approach with Applications to Cross-Modal Matching,” IEEE Trans. on Image Processing, Vol.25, No.8, pp. 3826-3837, 2016.
Cited by
8 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