Faculty of Computer Science and Technology
About this community
Current research areas include bioinformatics, computer architecture, computer vision, distributed systems, graphics and human-computer interaction, logic and semantics, machine learning, natural language processing, networking and wireless communication, operating systems and virtualization, programming, security, and sustainable computing
The Computer Laboratory undertakes research in a broad range of subjects within the disciplines of Computer Science, Engineering, Technology, and Mathematics. Current research areas include bioinformatics, computer architecture, computer vision, distributed systems, graphics and human-computer interaction, logic and semantics, machine learning, natural language processing, networking and wireless communication, operating systems and virtualization, programming, security, and sustainable computing.
Collections in this community
Recent Submissions
-
SmileNet: Registration-Free Smiling Face Detection in the Wild
(IEEE, 2017-10-29)We present a novel smiling face detection framework called SmileNet for detecting faces and recognising smiles in the wild. SmileNet uses a Fully Convolutional Neural Network (FCNN) to detect multiple smiling faces in a ... -
TCP in the Internet of Things: from ostracism to prominence
TCP has traditionally been neglected as a transport-layer protocol for the Internet of Things (IoT). However, recent trends and industry needs are favouring TCP presence in IoT environments. In this paper, we first motivate ... -
Verifying Spatial Properties of Array Computations
(ACM, 2017-10)Arrays computations are at the core of numerical modelling and computational science applications. However, low-level manipulation of array indices is a source of program error. Many practitioners are aware of the need to ... -
An Error-Oriented Approach to Word Embedding Pre-Training
(Association for Computational Linguistics, 2017-09-08)We propose a novel word embedding pre-training approach that exploits writing errors in learners' scripts. We compare our method to previous models that tune the embeddings based on script scores and the discrimination ...
