I am a Senior Lecturer in Computer Science at QMUL. I am head of the Applied Machine Learning Lab at QMUL, and a member of the Risk and Information Management (RIM) group, as well as the Centre for Intelligent Sensing. Previously I was a Lecturer ('12-15), and Postdoc ('08-11) coordinating the behaviour monitoring work package for the SAMURAI EU FP7 project at QMUL. During my PhD ('04-08), I worked with Sethu Vijayakumar in the Statistical Machine Learning and Motor Control group and Edinburgh's IPAB and ANC institutes.
My background spans informatics & neuroscience (PhD Neuroinformatics, Edinburgh, 2008; MSc Neuroinformatics, Edinburgh 2004), machine learning (MSc Informatics, Edinburgh, 2003) and computer science (BA Computer Science, University of Cambridge, 2002).
My research focuses on probabilistic modelling and machine learning, particularly life-long, transfer and active learning. I have looked at a variety application areas including computer vision (behaviour understanding, person re-identification, attribute and zero-shot learning), sensor fusion, robotics, motion-capture, novel human-computer interfaces, theoretical neuroscience and business data analytics
05/2014: EPSRC Grant Awarded
06/2014: 3x Papers accepted to ECCV 2014
07/2014: 2 papers on Open World Re-identification
01/2015: EU Horizon 2020 Grant DREAM awarded
02/2015: PAMI paper accepted: Record AwA ZSL results!
03/2015: 2x papers accepted to CVPR 2015!
03/2015: ICLR 2015 paper on multi-task/domain!
05/2015: UAI 2015 paper on Bayesian Net transfer!
06/2015: PAMI paper accepted on Robust Ranking!
07/2015: Welcome Chenyang Zhao to the lab
07/2015: BMVC 2015 Oral: Our Sketch recognition Deep Neural Network is the first to surpass human performance!
09/2015: Our BMVC'15 sketch recognition paper wins Best Science Paper prize!
09/2015: Welcome Marija Jegorova to the lab
02/2016: Expert Systems with Applications paper accepted
03/2016: Three CVPR'16 papers accepted including one Oral!
07/2016: One ECCV'16 paper accepted
07/2016: Two BMVC'16 papres accepted as Orals!
04/2016: For exceptional students, EECS has three full competitively-allocated PhD studentships this year (Autumn 2016 start).
Sample code for active learning & discovery (PAKDD'11,TKDE'11,ECCV'12)
Unsegmented sports news dataset available (ICDM'11). Includes reference extracted STIP features and ground-truth multi-label annotation.
Sample code for MCTM (ICCV'09, IJCV'11) and WSJTM (ACCV'10, PAMI'11)
Attribute Dataset for Heterogeneous Face Recognition (ACCV'14)
02/2015: Code for the famous ELF descriptor in re-id. First ever public release!
06/2015: Ground-truth Anomaly Annotation for ICCV'09 and IJCV'11 papers.
07/2015: Code for Sketch-a-Net BMVC'15 paper.
09/2015: Code for our ICLR'15 Multi-Task/Multi-domain paper
09/2015: Multi-camera video surveillance dataset from our TCSVT'15 paper
03/2016: 800K image+social metadata dataset from our ACM DH'16 paper
MSc, Neuroinformatics, University of Edinburgh, 2004
Thesis: Functional Organization & Plasticity in the Vestibulo-Ocular Reflex
Advisor: Mayank Dutia
MSc, Informatics, University of Edinburgh, 2003
Thesis: Optimal Learning in Neurons with Active Dendritic Spines
Advisor: David Barber
BA, Computer Science, University of Cambridge, 2002
Dissertation: A Probabilistic Approach for Commodity Eye-Tracking
* Best Dissertation Prize, University of Cambridge Computer Laboratory
* UK SET Computer Science Student of the Year Award
Advisor: David Mackay
Visit my Google Scholar Profile.