Thomas Verelst

4 papers · 2020–2026 · 3 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🏃 Academic Marathon · Sprint 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (10) 🐣 Hot Topic Early Bird

Venues

WACV (2) CVPR (1) ICCV (1)

Top co-authors

Tinne Tuytelaars (3) Jibril El Hassani (1) Paul K. Rubenstein (1) Marcin Eichner (1) Maxim Berman (1)

Research topics

Machine Learning (4) Application Areas (4) Computer Vision (3) Learning Types (2) Deep Learning (1) Analysis (1) Architectures (1) Core AI (1) Core Methods (1) Optimization & Theory (1) Processing (1)

Keywords

reinforcement learning (1) object detection (1) weakly supervised learning (1) multi-label classification (1) human pose estimation (1) neural network optimization (1) efficient computing (1) convolutional neural network (1) dense prediction (1) policy network (1) inference efficiency (1) video processing (1) inference speed (1) model efficiency (1) dynamic neural network (1) pareto optimization (1) dynamic convolution (1) block-sparse convolution (1) onnx deployment (1) spatial sparsity (1)

Papers

DualRes: Production-ready Dynamic Object Detection WACV 2026 Spatial Consistency Loss for Training Multi-Label Classifiers From Single-Label Annotations WACV 2023 BlockCopy: High-Resolution Video Processing With Block-Sparse Feature Propagation and Online Policies ICCV 2021 Dynamic Convolutions: Exploiting Spatial Sparsity for Faster Inference CVPR 2020