no code implementations • 19 Dec 2023 • Leander van den Heuvel, Gertjan Burghouts, David W. Zhang, Gwenn Englebienne, Sabina B. van Rooij
For object detection, it is possible to view the prediction of bounding boxes as a reverse diffusion process.
1 code implementation • 2 Nov 2023 • Elisa Nguyen, Meike Nauta, Gwenn Englebienne, Christin Seifert
We present \textit{Temporal Spike Attribution} (TSA), a local explanation method for SNNs.
no code implementations • 26 Jul 2019 • Andrea Papenmeier, Gwenn Englebienne, Christin Seifert
We also found that users cannot be tricked by high-fidelity explanations into having trust for a bad classifier.
no code implementations • WS 2019 • Rob Koopman, Sheng-Hui Wang, Gwenn Englebienne
The embedding of words and documents in compact, semantically meaningful vector spaces is a crucial part of modern information systems.
no code implementations • 14 Aug 2017 • Jaebok Kim, Khiet P. Truong, Gwenn Englebienne, Vanessa Evers
In this paper, we propose to use deep 3-dimensional convolutional networks (3D CNNs) in order to address the challenge of modelling spectro-temporal dynamics for speech emotion recognition (SER).
no code implementations • 13 Aug 2017 • Jaebok Kim, Gwenn Englebienne, Khiet P. Truong, Vanessa Evers
In order to improve the generalisation capabilities of the emotion models, we propose to use Multi-Task Learning (MTL) and use gender and naturalness as auxiliary tasks in deep neural networks.
no code implementations • 6 Mar 2015 • Ninghang Hu, Gwenn Englebienne, Zhongyu Lou, Ben Kröse
The model is embedded with a latent layer that is able to capture a richer class of contextual information in both state-state and observation-state pairs.