Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Emadeldeen Hamdan

Emadeldeen Hamdan

1 indexed paper

Recent (6 mo)
1
With code
0
Influential cites
0
Benchmarked
0

Publications per year

1
26

Top categories

Vision×1Image and Video Processing×1Signal Processing×1

Frequent co-authors

Prathyush Sajith1×
Ahmet Enis Cetin1×

Research Timeline

2026
WHTMix: Efficient Stereo Depth Estimation via Walsh-Hadamard Token Mixing

Replacing global self-attention in stereo transformers with a data-independent Walsh-Hadamard token mixer reduces compute and latency by a factor of 2.46 and 2.65 respectively.

Highlighted terms show continued research focus across papers

Papers

cs.CVeess.IVeess.SPEmpiricalRecentJul 28, 2026

WHTMix: Efficient Stereo Depth Estimation via Walsh-Hadamard Token Mixing

Prathyush Sajith, Emadeldeen Hamdan, Ahmet Enis Cetin

Replacing global self-attention in stereo transformers with a data-independent Walsh-Hadamard token mixer reduces compute and latency by a factor of 2.46 and 2.65 respectively.

View →