Efficient Mixed Generative Using Semantic Cross Media Hashing Methods
DOI:
https://doi.org/10.26438/ijcse/v6i8.243246Keywords:
Fisher Vector, Ranking, Semantic Hashing Method, Skip Gram, Word EmbeddingAbstract
Hash methods are useful for number of tasks and have attracted large attention in recent times. They proposed different approaches to capture the similarities between text and images. Most of the existing work uses bag-of-words method to represent text information. Since words with different format may have same meaning, the similarities of the semantic text cannot be well worked out in these methods. To overcome these challenges, a new method called Semantic Cross Media Hashing (SCMH) is proposed that uses the continuous representations of words which captures the semantic textual similarity level and uses a Deep Belief Network (DBN) to build the correlation between different modes. In this method we use Skipgram algorithm for word embedding, Scale Invariant Feature Transform(SIFT) descriptor to extract the key points from the images and MD5 algorithm for hash code generation. To demonstrate the effectiveness of the proposed method, it is necessary to consider data sets that are basic. Experimental results shows that the proposed method achieves significantly better results as well as the effectiveness of the proposed method is similar or superior to other hash methods.
References
[1] Y. Gong, S. Lazebnik, A. Gordo, and F. Perronnin, “Iterative quantization: A procrustean approach to learning binary codes for large-scale image retrieval,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 35, no. 12, pp. 2916–2929, Dec. 2013.
[2] Y. Pan, T. Yao, T. Mei, H. Li, C.-W. Ngo, and Y. Rui, “Clickthrough-based cross-view learning for image search,” in Proc. 37th Int.ACMSIGIR Conf. Res. Develop. Inf. Retrieval, 2014, pp. 717–726.
[3] D. Zhai, H. Chang, Y. Zhen, X. Liu, X. Chen, and W. Gao, “Parametric local multimodal hashing for cross-view similarity search,” in Proc. 23rd Int. Joint Conf. Artif. Intell., 2013, pp. 2754–2760.
[4] G. Ding, Y. Guo, and J. Zhou, “Collective matrix factorization hashing for multimodal data,” in Proc. IEEE Conf. Comput. Vis. Pattern Recog., 2014, pp. 2083–2090.
[5] H. J_egou, F. Perronnin, M. Douze, J. S_anchez, P. P_erez, and C. Schmid, “Aggregating local image descriptors into compact codes,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 34, no. 9, pp. 1704–1716, Sep. 2011.
[6] J. Zhou, G. Ding, and Y. Guo, “Latent semantic sparse hashing for cross-modal similarity search,” in Proc. 37th Int. ACM SIGIR Conf. Res. Develop. Inf. Retrieval, 2014, pp. 415–424.
[7] Z. Yu, F. Wu, Y. Yang, Q. Tian, J. Luo, and Y. Zhuang, “Discriminative coupled dictionary hashing for fast cross-media retrieval,” in Proc. 37th Int. ACM SIGIR Conf. Res. Develop. Inf.
Retrieval, 2014, pp. 395–404.
[8] H. Zhang, J. Yuan, X. Gao, and Z. Chen, “Boosting cross-media retrieval via visual-auditory feature analysis and relevance feedback,” in Proc. ACM Int. Conf. Multimedia, 2014, pp. 953–956.
[9] A. Karpathy and L. Fei-Fei, “Deep visual-semantic alignments for generating image descriptions,” in Proc. IEEE Conf. Comput. Vis. Pattern Recog., Boston, MA, USA, Jun. 2015, pp. 3128–3137.
[10] J. Song, Y. Yang, Y. Yang, Z. Huang, and H. T. Shen, “Inter-media hashing for large-scale retrieval from heterogeneous data sources,” in Proc. Int. Conf. Manage. Data, 2013, pp. 785–79
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors contributing to this journal agree to publish their articles under the Creative Commons Attribution 4.0 International License, allowing third parties to share their work (copy, distribute, transmit) and to adapt it, under the condition that the authors are given credit and that in the event of reuse or distribution, the terms of this license are made clear.
