Over the last years deep learning methods have been shown to outperform previous state-of-the-art machine learning techniques\nin several fields, with computer vision being one of the most prominent cases. This review paper provides a brief overview of some\nof the most significant deep learning schemes used in computer vision problems, that is, Convolutional Neural Networks, Deep\nBoltzmann Machines and Deep Belief Networks, and Stacked Denoising Autoencoders. A brief account of their history, structure,\nadvantages, and limitations is given, followed by a description of their applications in various computer vision tasks, such as object\ndetection, face recognition, action and activity recognition, and human pose estimation. Finally, a brief overview is given of future\ndirections in designing deep learning schemes for computer vision problems and the challenges involved therein.
Loading....