BLSTM Recurrent Neural Network for Object Recognition
DOI: 10.23977/jaip.2016.11005 | Downloads: 55 | Views: 2858
Yalan Qin 1
1 College of Computer and Information Science, Southwest University, Chongqing, 400715, China
Corresponding AuthorYalan Qin
Multi-object relationship information can help eliminate some incorrect combinations or locations of objects. Moreover, it is favorable to extract scene information for object recognition. In this paper, we introduce a new way to generate image representation and propose a deep learning framework to fuse the contextual dependencies among objects and scene information in an image. It adopts a bidirectional long short-term memory recurrent neural network (BLSTM-RNN) to deal with the problem of variable-length sequence produced by local detectors in different images. Then it is applied to the existing tree context model for further recognition. Experimental results on SUN09 dataset show that our model outperforms the state-of the-art object localization methods.
KEYWORDSMulti-object Relationship; Object Recognition; BLSTM
CITE THIS PAPER
Yalan Q. (2016) BLSTM Recurrent Neural Network for Object Recognition. Journal of Artificial Intelligence Practice (2016) 1: 25-29.
 P. F. Felzenszwalb, R. B. Girshick, D. McAllester, and D. Ramanan, “Object detection with discriminatively trained part-based models,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 32, no. 9, pp. 1627–1645, Sep. 2010.
 D. Hoiem, A. A. Efros, and M. Hebert, “Putting objects in perspective,”Int. J. Comput. Vis., vol. 80, no. 1, pp. 3–15, 2008.
 Graves A, Schmidhuber J. Framewise phoneme classification with bidirectional LSTM and other neural network architectures[J]. Neural Networks, 2005, 18(5): 602-610.
 M. J. Choi, J. J. Lim, A. Torralba, and A. S. Willsky, “Exploiting hierarchical context on a large database of object categories,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), San Francisco, CA, USA,Jun. 2010, pp. 129–136.
 Doetsch P, Kozielski M, Ney H. Fast and robust training of recurrent neural networks for offline handwriting recognition [C]//Frontiers in Handwriting Recognition (ICFHR), 2014 14th International Conference on. IEEE, 2014: 279-284.
 M. J. Choi, A. Torralba, and A. S. Willsky, “A tree-based context model for object recognition,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 34,no. 2, pp. 240–252, Feb. 2012.