SpecTrHuMS: Spectral transformer for human mesh sequence learning

We present SpecTrHuMS, a Spectral Transformer for 3D triangular Human Mesh Sequence learning which combines known deep learning models with spectral mesh processing to capture characteristics of 3D shapes as well as temporal dependencies between the frames. Unlike previous works in this field, our a...

Celý popis

Podrobná bibliografie

Vydáno v:	Computers & graphics Ročník 115; s. 191 - 203
Hlavní autoři:	Lemeunier, Clément, Denis, Florence, Lavoué, Guillaume, Dupont, Florent
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	Elsevier Ltd 01.10.2023 Elsevier
Témata:	Autoencoder Computer Science Computer Vision and Pattern Recognition Geometric deep learning Human body triangular mesh sequences Machine Learning Spectral analysis Transformers Transformers Geometric deep learning Autoencoder Human body triangular mesh sequences Spectral analysis Geometric Deep Learning
ISSN:	0097-8493
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!