Existing action recognition methods are typically actor-specific due to ...
Rising concerns about privacy and anonymity preservation of deep learnin...
Representation learning for sketch-based image retrieval has mostly been...
Fine-grained categories that largely share the same set of parts cannot ...
Humans show high-level of abstraction capabilities in games that require...
The efficacy of zero-shot sketch-based image retrieval (ZS-SBIR) models ...
Most of the existing Zero-Shot Learning (ZSL) methods focus on learning ...
Existing self-supervised learning methods learn representation by means ...
Zero-Shot Learning (ZSL) aims to recognise unseen object classes, which ...
We propose bookworm continual learning(BCL), a flexible setting where un...
Low-shot sketch-based image retrieval is an emerging task in computer vi...
The information bottleneck principle provides an information-theoretic m...
In this paper, we investigate the problem of zero-shot sketch-based imag...
Zero-shot sketch-based image retrieval (SBIR) is an emerging task in com...
Despite being very successful within the pattern recognition and machine...
In this work we introduce a cross modal image retrieval system that allo...
Graph-based methods are known to be successful in many machine learning ...
Offline signature verification is one of the most challenging tasks in
b...
Many algorithms formulate graph matching as an optimization of an object...
Graph-based methods are known to be successful for pattern description a...