CROMA: Remote sensing representations with contrastive radar-optical masked autoencoders

A Fuller, K Millard, J Green - Advances in Neural …, 2024 - proceedings.neurips.cc
A vital and rapidly growing application, remote sensing offers vast yet sparsely labeled,
spatially aligned multimodal data; this makes self-supervised learning algorithms invaluable …

Spiking tucker fusion transformer for audio-visual zero-shot learning

W Li, P Wang, R **ong, X Fan - IEEE Transactions on Image …, 2024 - ieeexplore.ieee.org
The spiking neural networks (SNNs) that efficiently encode temporal sequences have shown
great potential in extracting audio-visual joint feature representations. However, coupling …