Few-shot object detection (FSOD) identifies objects from extremely few
a...
Zero-shot learning (ZSL) aims to recognize the novel classes which canno...
The key challenge of zero-shot learning (ZSL) is how to infer the latent...
Zero-shot learning (ZSL) tackles the novel class recognition problem by
...
Generalized zero-shot learning (GZSL) has achieved significant progress,...
Visual images usually contain the informative context of the environment...
Generative adversarial networks (GANs) have been a popular deep generati...
Dynamic texture (DT) exhibits statistical stationarity in the spatial do...
Conventional approaches used supervised learning to estimate off-line wr...