no code implementations • 19 May 2022 • Syed Sameed Husain, Eng-Jon Ong, Dmitry Minskiy, Mikel Bober-Irizar, Amaia Irizar, Miroslaw Bober
Unravelling protein distributions within individual cells is key to understanding their function and state and indispensable to developing new treatments.
no code implementations • 9 Jul 2021 • Eng-Jon Ong, Sameed Husain, Miroslaw Bober
However, this requires the knowledge of the distributions of the activations of aggregation layers.
no code implementations • 12 Jul 2019 • Syed Sameed Husain, Eng-Jon Ong, Miroslaw Bober
We propose a novel CNN architecture called ACTNET for robust instance image retrieval from large-scale datasets.
no code implementations • 3 Jul 2018 • Eng-Jon Ong, Sameed Husain, Mikel Bober-Irizar, Miroslaw Bober
This work addresses the problem of accurate semantic labelling of short videos.
no code implementations • 13 Jul 2017 • Mikel Bober-Irizar, Sameed Husain, Eng-Jon Ong, Miroslaw Bober
We investigate factors controlling DNN diversity in the context of the Google Cloud and YouTube-8M Video Understanding Challenge.
no code implementations • 1 Feb 2017 • Eng-Jon Ong, Sameed Husain, Miroslaw Bober
To achieve this, we propose a novel Siamese network.
no code implementations • CVPR 2016 • Eng-Jon Ong, Miroslaw Bober
To this end, we propose a novel, unsupervised approach to thresholded search in Hamming space, supporting long codes (e. g. 512-bits) with a wide-range of Hamming distance radii.
no code implementations • CVPR 2014 • Eng-Jon Ong, Oscar Koller, Nicolas Pugeault, Richard Bowden
This paper tackles the problem of spotting a set of signs occuring in videos with sequences of signs.