Khan Muhammad

TL;DR: Experimental results demonstrate that features representation using CNN and auto-encoder shows much better results than several state-of-the-art hashing schemes for image retrieval on mobile devices.

TL;DR: This work provides a detailed review of computer vision-based methods for WCE videos analysis with an emphasis placed on future research directions towards smarter healthcare and personalization.

TL;DR: In this article, a 3D realistic open-ended VR and Kinect sensor-based training setup using the Unity game engine is proposed for road safety training for children, where children are educated and involved in road safety exercises.

TL;DR: An object-oriented feature selection mechanism for deep convolutional features from a pre-trained CNN that achieves better precision and recall than the full feature set for objects with varying backgrounds and reduces number of feature maps without performance degradation.

TL;DR: The proposed model exploits the Heterogeneous Bibliographic Network (HBN) to generate personalized citation recommendations and utilizes semantic relations corresponding to the objects of the heterogeneous bibliographic network and captures network structure proximity employing the Scientific Paper Embeddings using Citation-informed Transformers and Denoising Auto-encoder networks to learn semantic-preserving graph representations.