S
Syed Afaq Ali Shah
Researcher at Murdoch University
Publications - 66
Citations - 1341
Syed Afaq Ali Shah is an academic researcher from Murdoch University. The author has contributed to research in topics: Deep learning & Convolutional neural network. The author has an hindex of 16, co-authored 66 publications receiving 825 citations. Previous affiliations of Syed Afaq Ali Shah include Central Queensland University & University of Western Australia.
Papers
More filters
Book
A Guide to Convolutional Neural Networks for Computer Vision
TL;DR: This self-contained guide will benefit those who seek to both understand the theory behind CNNs and to gain hands-on experience on the application of CNNs in computer vision, providing a comprehensive introduction to CNNs.
Journal ArticleDOI
Iterative deep learning for image set based face and object recognition
TL;DR: An Iterative Deep Learning Model (IDLM) that automatically and hierarchically learns discriminative representations from raw face and object images is proposed that achieves the best performance on all these datasets.
Proceedings Article
Attention in convolutional LSTM for gesture recognition
TL;DR: A new variant of L STM is derived, in which the convolutional structures are only embedded into the input-to-state transition of LSTM, and it is demonstrated that the spatial convolutions in the three gates scarcely contribute to the spatiotemporal feature fusion, and the attention mechanisms embedded in the input and output gates cannot improve the feature fusion.
Journal ArticleDOI
Continuous Gesture Segmentation and Recognition Using 3DCNN and Convolutional LSTM
TL;DR: An effective deep architecture for continuous gesture recognition is presented and a balanced squared hinge loss function is proposed to deal with the imbalance between boundaries and nonboundaries.
Journal ArticleDOI
Block Level Skip Connections Across Cascaded V-Net for Multi-Organ Segmentation
Liang Zhang,Jiaming Zhang,Peiyi Shen,Guangming Zhu,Ping Li,Xiaoyuan Lu,Huan Zhang,Syed Afaq Ali Shah,Mohammed Bennamoun +8 more
TL;DR: This work proposes an efficient cascaded V-Net model that can take full advantage of features from the first stage network and make the cascaded structure more efficient, and combines stacked small and large kernels with an inception-like structure to help the model to learn more patterns.