Dual-view ranking with hardness assessment for zero-shot learning
Zero-shot learning (ZSL) is to build recognition models for previously unseen target classes
which have no labeled data for training by transferring knowledge from some other related …
which have no labeled data for training by transferring knowledge from some other related …
Inductive zero-shot image annotation via embedding graph
F Wang, J Liu, S Zhang, G Zhang, Y Li, F Yuan - IEEE Access, 2019 - ieeexplore.ieee.org
Conventional image annotation systems can only handle those images having labels within
the exist library, but cannot recognize those novel labels. In order to learn new concepts …
the exist library, but cannot recognize those novel labels. In order to learn new concepts …
[PDF][PDF] Zero-shot Learning with Many Classes by High-rank Deep Embedding Networks.
Zero-shot learning (ZSL) is a recently emerging research topic which aims to build
classification models for unseen classes with knowledge transferred from auxiliary seen …
classification models for unseen classes with knowledge transferred from auxiliary seen …