< Back to previous page
Researcher
Thomas Verelst
- Disciplines:Computer vision
Affiliations
- Processing Speech and Images (PSI) (Division)
Member
From1 Aug 2020 → 31 Jan 2023 - ESAT - PSI, Processing Speech and Images (Division)
Member
From1 Oct 2018 → 31 Jul 2020
Projects
1 - 1 of 1
- Spatially Adaptive Neural Networks for Computer VisionFrom1 Oct 2018 → 26 Jan 2023Funding: Own budget, for example: patrimony, inscription fees, gifts
Publications
1 - 6 of 6
- Spatially Adaptive Neural Networks for Computer Vision(2023)
Authors: Thomas Verelst, Tinne Tuytelaars
- Computer vision and human behaviour, emotion and cognition detection: A use case on student engagement(2021)
Authors: Pieter Vanneste, Thomas Verelst, Tinne Tuytelaars, Annelies Raes, Fien Depaepe, Wim Van Den Noortgate
Pages: 1 - 20 - SegBlocks: Towards block-based adaptive resolution networks for fast segmentation(2021)
Authors: Thomas Verelst, Tinne Tuytelaars
Pages: 18 - 22 - Processor Architecture Optimization for Spatially Dynamic Neural Networks(2021)
Authors: Steven Colleman, Thomas Verelst, Linyan Mei, Tinne Tuytelaars, Marian Verhelst
Number of pages: 6 - BlockCopy: High-resolution video processing with block-sparse feature propagation and online policies(2021)
Authors: Thomas Verelst, Tinne Tuytelaars
Pages: 5138 - 5147 - Dynamic convolutions: Exploiting spatial sparsity for faster inference(2020)
Authors: Thomas Verelst, Tinne Tuytelaars
Pages: 2317 - 2326