User profiles for B Fernando

Basura Fernando

Scientist at A*STAR Singapore, Assistant Professor at NTU
Verified email at ihpc.a-star.edu.sg
Cited by 10008

[HTML][HTML] Alzheimer's disease: a journey from amyloid peptides and oxidative stress, to biomarker technologies and disease prevention strategies—gains from AIBL …

…, B Brown, SL Gardener, B Fernando… - Journal of …, 2018 - content.iospress.com
Worldwide there are over 46 million people living with dementia, and this number is expected
to double every 20 years reaching about 131 million by 2050. The cost to the community …

Adverse drug events in the elderly

KM Cresswell, B Fernando, B McKinstry… - British medical …, 2007 - academic.oup.com
… Not all ADEs are, however, preventable; some side effects are, for example, unpredictable
(Type B idiosyncratic reactions) and these cannot therefore be currently prevented. …

Interventions for reducing medication errors in children in hospital

…, H Vermeulen, B Apampa, B Fernando… - Cochrane Database …, 2015 - cochranelibrary.com
b Total number of admission days on intervention and control wards in the pre‐intervention
and … b Admission days on intervention and control wards in the pre‐intervention and post‐…

Spice: Semantic propositional image caption evaluation

P Anderson, B Fernando, M Johnson… - Computer Vision–ECCV …, 2016 - Springer
… Instead, they were asked to evaluate caption triples by identifying ‘Which of the sentences,
B or C, is more similar to sentence A?’, where sentence A is a reference caption, and B and C …

Unsupervised visual domain adaptation using subspace alignment

B Fernando, A Habrard, M Sebban… - Proceedings of the …, 2013 - openaccess.thecvf.com
In this paper, we introduce a new domain adaptation (DA) algorithm where the source and
target domains are represented by subspaces described by eigenvectors. In this context, our …

Dynamic image networks for action recognition

H Bilen, B Fernando, E Gavves… - Proceedings of the …, 2016 - openaccess.thecvf.com
… We show here that the construction of Fernando et al. [6] can be used to obtain exactly such
an image. The idea of their paper is to represent a video as a ranking function for its frames …

Modeling video evolution for action recognition

B Fernando, E Gavves, JM Oramas… - Proceedings of the …, 2015 - openaccess.thecvf.com
… For MA, we observe two facts; first, the output signal is much smoother (see Figure 3(b))
and … Plotting these two variables for a window T=50 in Figure 3(b), we observe a smoother …

Guiding the long-short term memory model for image caption generation

X Jia, E Gavves, B Fernando… - Proceedings of the …, 2015 - openaccess.thecvf.com
In this work we focus on the problem of image caption generation. We propose an extension
of the long short term memory (LSTM) model, which we coin gLSTM for short. In particular, …

Self-supervised video representation learning with odd-one-out networks

B Fernando, H Bilen, E Gavves… - Proceedings of the …, 2017 - openaccess.thecvf.com
We propose a new self-supervised CNN pre-training technique based on a novel auxiliary
task called odd-one-out learning. In this task, the machine is asked to identify the unrelated or …

Rank pooling for action recognition

B Fernando, E Gavves, J Oramas… - IEEE transactions on …, 2016 - ieeexplore.ieee.org
… where AS is a ranking algorithm with uniform stability b learned from the set of samples S. …
function c=i with an error no larger than b compared to the c learned when all frames are …