2015 10th International Conference on Broadband and Wireless Computing, Communication and Applications (BWCCA) (2015)
Nov. 4, 2015 to Nov. 6, 2015
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/BWCCA.2015.63
Inspired by recent advances in deep learning, this paper reviews the deep learning methodologies and its applications in object tracking. To overcome the complexity and low-efficiency of existing full-connected deep learning based tracker, we use a novel convolutional deep belief network (CDBN) with convolution, weights sharing and pooling to have much fewer parameters, in addition to gain translation invariance which would benefit the tracker performance. Empirical evaluation demonstrates our CDBN based tracker outperforms several state-of-the-art methods on an open tracker benchmark.
Machine learning, Visualization, Convolution, Feature extraction, Kernel, Training, Neural networks
D. Hu, X. Zhou, X. Yu and Z. Hou, "Study on Deep Learning and Its Application in Visual Tracking," 2015 10th International Conference on Broadband and Wireless Computing, Communication and Applications (BWCCA), Krakow, Poland, 2015, pp. 240-246.