1 code implementation • 25 Sep 2019 • Julien Schroeter, Kirill Sidorov, Dave Marshall
This work addresses the long-standing problem of robust event localization in the presence of temporally of misaligned labels in the training data.
no code implementations • 16 Aug 2019 • Thomas Hartley, Kirill Sidorov, Christopher Willis, David Marshall
As Convolutional Neural Networks embed themselves into our everyday lives, the need for them to be interpretable increases.
no code implementations • 17 May 2019 • Julien Schroeter, Kirill Sidorov, David Marshall
We propose a novel model for temporal detection and localization which allows the training of deep neural networks using only counts of event occurrences as training labels.