Personal information

Activities

Works (8)

Spatially Adaptive Neural Networks for Computer Vision

2023-01-26 | Dissertation or Thesis
SOURCE-WORK-ID:

3961653

Contributors: Thomas Verelst; Tinne Tuytelaars
Source: check_circle
KU Leuven

Computer Vision and Human Behaviour, Emotion and Cognition Detection: A Use Case on Student Engagement

Mathematics
2021-02 | Journal article | Author
Contributors: Pieter Vanneste; José Oramas; Thomas Verelst; Tinne Tuytelaars; Annelies Raes; fien depaepe; wim van den noortgate
Source: check_circle
Multidisciplinary Digital Publishing Institute
grade
Preferred source (of 2)‎

Dynamic convolutions: Exploiting spatial sparsity for faster inference

Proceedings / CVPR, IEEE Computer Society Conference on Computer Vision and Pattern Recognition. IEEE Computer Society Conference on Computer Vision and Pattern Recognition
2020 | Conference paper
SOURCE-WORK-ID:

3304306

Part of ISSN: 2575-7075
WOSUID:

WOS:000620679502058

Contributors: Thomas Verelst; Tinne Tuytelaars
Source: check_circle
KU Leuven

Generating superpixels using deep image representations.

CoRR
2019 | Interactive resource
SOURCE-WORK-ID:

3311283

Contributors: Thomas Verelst; Matthew Blaschko; Maxim Berman
Source: check_circle
KU Leuven

Generating superpixels with deep representations

2018-06-18 | Lecture
SOURCE-WORK-ID:

1989926

Contributors: Thomas Verelst; Maxim Berman; Matthew Blaschko
Source: check_circle
KU Leuven

BlockCopy: High-resolution video processing with block-sparse feature propagation and online policies

Proceedings / IEEE International Conference on Computer Vision. IEEE International Conference on Computer Vision
Conference paper
SOURCE-WORK-ID:

3548926

Part of ISSN: 2380-7504
WOSUID:

WOS:000797698905036

Contributors: Thomas Verelst; Tinne Tuytelaars
Source: check_circle
KU Leuven

Processor Architecture Optimization for Spatially Dynamic Neural Networks

IEEE/IFIP International Conference on VLSI and System-on-Chip, VLSI-SoC
Conference paper
SOURCE-WORK-ID:

3774674

Part of ISSN: 2324-8440
WOSUID:

WOS:000814059800005

Contributors: Steven Colleman; Thomas Verelst; Linyan Mei; Tinne Tuytelaars; Marian Verhelst
Source: check_circle
KU Leuven

SegBlocks: Towards block-based adaptive resolution networks for fast segmentation

Lecture Notes in Artificial Intelligence
Conference paper
SOURCE-WORK-ID:

3393202

Part of ISSN: 0302-9743
Contributors: Thomas Verelst; Tinne Tuytelaars
Source: check_circle
KU Leuven