Abstract
Multi-modal retrieval is emerging as a new search paradigm that enables seamless information retrieval from various types of media. For example, users can simply snap a movie poster to search relevant reviews and trailers. To solve the problem, a set of mapping functions are learned to project high-dimensional features extracted from data of different media types into a common low-dimensional space so that metric distance measures can be applied. In this paper, we propose an effective mapping mechanism based on deep learning (i.e., stacked auto-encoders) for multi-modal retrieval. Mapping functions are learned by optimizing a new objective function, which captures both intra-modal and inter-modal semantic relationships of data from heterogeneous sources effectively. Compared with previous works which require a substantial amount of prior knowledge such as similarity matrices of intra-modal data and ranking examples, our method requires little prior knowledge. Given a large training dataset, we split it into mini-batches and continually adjust the mapping functions for each batch of input. Hence, our method is memory efficient with respect to the data volume. Experiments on three real datasets illustrate that our proposed method achieves significant improvement in search accuracy over the state-of-the-art methods.
- M. M. Bronstein, A. M. Bronstein, F. Michel, and N. Paragios. Data fusion through cross-modality metric learning using similarity-sensitive hashing. In CVPR, pages 3594--3601, 2010.Google ScholarCross Ref
- T.-S. Chua, J. Tang, R. Hong, H. Li, Z. Luo, and Y.-T. Zheng. Nus-wide: A real-world web image database from national university of singapore. In Proc. of ACM Conf. on Image and Video Retrieval (CIVR'09), Santorini, Greece., July 8-10, 2009. Google ScholarDigital Library
- J. Dean, G. Corrado, R. Monga, K. Chen, M. Devin, Q. V. Le, M. Z. Mao, M. Ranzato, A. W. Senior, P. A. Tucker, K. Yang, and A. Y. Ng. Large scale distributed deep networks. In NIPS, pages 1232--1240, 2012.Google ScholarDigital Library
- R. Goroshin and Y. LeCun. Saturating auto-encoder. CoRR, abs/1301.3577, 2013.Google Scholar
- G. Hinton. A Practical Guide to Training Restricted Boltzmann Machines. Technical report, 2010.Google Scholar
- G. R. Hjaltason and H. Samet. Index-driven similarity search in metric spaces. ACM Trans. Database Syst., 28(4):517--580, 2003. Google ScholarDigital Library
- M. J. Huiskes and M. S. Lew. The mir flickr retrieval evaluation. In Multimedia Information Retrieval, pages 39--43, 2008. Google ScholarDigital Library
- A. Krizhevsky. Learning multiple layers of features from tiny images. Technical report, 2009.Google Scholar
- S. Kumar and R. Udupa. Learning hash functions for cross-view similarity search. In IJCAI, pages 1360--1365, 2011. Google ScholarDigital Library
- Y. LeCun, L. Bottou, G. Orr, and K. Müller. Efficient BackProp. In G. Orr and K.-R. Müller, editors, Neural Networks: Tricks of the Trade, volume 1524 of Lecture Notes in Computer Science, chapter 2, pages 9--50. Springer Berlin Heidelberg, Berlin, Heidelberg, Mar. 1998. Google ScholarDigital Library
- W. Liu, J. Wang, S. Kumar, and S.-F. Chang. Hashing with graphs. In ICML, pages 1--8, 2011.Google ScholarDigital Library
- X. Lu, F. Wu, S. Tang, Z. Zhang, X. He, and Y. Zhuang. A low rank structural large margin method for cross-modal ranking. In SIGIR, pages 433--442, 2013. Google ScholarDigital Library
- A. L. Maas, Q. V. Le, T. M. O'Neil, O. Vinyals, P. Nguyen, and A. Y. Ng. Recurrent neural networks for noise reduction in robust asr. In INTERSPEECH, 2012.Google ScholarCross Ref
- C. D. Manning, P. Raghavan, and H. Schütze. Introduction to information retrieval, pages 151--175. Cambridge University Press, 2008. Google ScholarDigital Library
- J. Ngiam, A. Khosla, M. Kim, J. Nam, H. Lee, and A. Y. Ng. Multimodal deep learning. In ICML, pages 689--696, 2011.Google ScholarDigital Library
- N. Rasiwasia, J. C. Pereira, E. Coviello, G. Doyle, G. R. G. Lanckriet, R. Levy, and N. Vasconcelos. A new approach to cross-modal multimedia retrieval. In ACM Multimedia, pages 251--260, 2010. Google ScholarDigital Library
- S. Rifai, P. Vincent, X. Muller, X. Glorot, and Y. Bengio. Contractive auto-encoders: Explicit invariance during feature extraction. In ICML, pages 833--840, 2011.Google ScholarDigital Library
- R. Salakhutdinov and G. E. Hinton. Semantic hashing. Int. J. Approx. Reasoning, 50(7):969--978, 2009. Google ScholarDigital Library
- R. Socher, J. Pennington, E. H. Huang, A. Y. Ng, and C. D. Manning. Semi-supervised recursive autoencoders for predicting sentiment distributions. In EMNLP, pages 151--161, 2011. Google ScholarDigital Library
- J. Song, Y. Yang, Y. Yang, Z. Huang, and H. T. Shen. Inter-media hashing for large-scale retrieval from heterogeneous data sources. In SIGMOD Conference, pages 785--796, 2013. Google ScholarDigital Library
- N. Srivastava and R. Salakhutdinov. Multimodal learning with deep boltzmann machines. In NIPS, pages 2231--2239, 2012.Google Scholar
- P. Vincent, H. Larochelle, Y. Bengio, and P.-A. Manzagol. Extracting and composing robust features with denoising autoencoders. In ICML, pages 1096--1103, 2008. Google ScholarDigital Library
- R. Weber, H.-J. Schek, and S. Blott. A quantitative analysis and performance study for similarity-search methods in high-dimensional spaces. In VLDB, pages 194--205, 1998. Google ScholarDigital Library
- Y. Weiss, A. Torralba, and R. Fergus. Spectral hashing. In NIPS, pages 1753--1760, 2008.Google ScholarDigital Library
- Y. Zhen and D.-Y. Yeung. A probabilistic model for multimodal hash function learning. In KDD, pages 940--948, 2012. Google ScholarDigital Library
- X. Zhu, Z. Huang, H. T. Shen, and X. Zhao. Linear cross-modal hashing for efficient multimodal search. MM, 2013. Google ScholarDigital Library
- Y. Zhuang, Y. Yang, and F. Wu. Mining semantic correlation of heterogeneous multimedia data for cross-media retrieval. IEEE Transactions on Multimedia, 10(2):221--229, 2008. Google ScholarDigital Library
Index Terms
- Effective multi-modal retrieval based on stacked auto-encoders
Recommendations
Lossless-constraint Denoising based Auto-encoders
In this paper, we address the poor generalization ability problem of traditional auto-encoder on noise data, and propose a Lossless-constraint Denoising (LD) method, which can enhance the anti-noise ability and robustness of auto-encoders. We ...
Effective deep learning-based multi-modal retrieval
Multi-modal retrieval is emerging as a new search paradigm that enables seamless information retrieval from various types of media. For example, users can simply snap a movie poster to search for relevant reviews and trailers. The mainstream solution to ...
Re-ranking by multi-modal relevance feedback for content-based social image retrieval
APWeb'12: Proceedings of the 14th Asia-Pacific international conference on Web Technologies and ApplicationsWith the recent rapid growth of social image hosting websites, it is becoming increasingly easy to construct a large database of tagged images. In this paper, we investigate whether and how social tags can be used for improving content-based image ...
Comments