Author

Tomas Wilkinson

h-index 0 View on Semantic Scholar

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Oct 2026

Event-based Action Recognition by Pre-Training on Multi-Frame Representations

This work adopts a masked auto-encoding framework to pre-train a Vision Transformer using a sparsity-aware masking algorithm and token selection mechanism to improve downstream performance and control computational complexity.

E. Norrby, Tomas Wilkinson, P. Nyblom et al. · 0 citations

Open access 2026

Generalized CSTR: Multi-Dimensional Representations for Event-Based Vision

This study proposes a Generalized Compact Spatio-Temporal Representation (gCSTR), a simple yet effective extension of the CSTR that enhances temporal expressiveness by constructing complementary representations in the spatio-temporal $xt$ and $yt$ projection planes that preserve the fine-grained temporal structure whil...

Per Nyblom, David Gustafsson, Tomas Wilkinson · IEEE Access · 0 citations