Few-shot image classification is a challenging problem that aims to achieve the human level
of recognition based only on a small number of training images. One main solution to few …

A two-stage training paradigm consisting of sequential pre-training and meta-training stages
has been widely used in current few-shot learning (FSL) research. Many of these methods …

Abstract Vision Transformers (ViTs) emerge to achieve impressive performance on many
data-abundant computer vision tasks by capturing long-range dependencies among local …

Few-shot learning is a challenging problem since only a few examples are provided to
recognize a new class. Several recent studies exploit additional semantic information, eg …

Abstract" A picture is worth a thousand words", significantly beyond mere a categorization.
Accompanied by that, many patches of the image could have completely irrelevant …

Single image-level annotations only correctly describe an often small subset of an image's
content, particularly when complex real-world scenes are depicted. While this might be …

It is natural to represent objects in terms of their parts. This has the potential to improve the
performance of algorithms for object recognition and segmentation but can also help for …

While the majority of FSL models focus on image classification, the extension to action
recognition is rather challenging due to the additional temporal dimension in videos. To …

This paper presents new hierarchically cascaded transformers that can improve data
efficiency through attribute surrogates learning and spectral tokens pooling. Vision …

Recently, few-shot action recognition receives increasing attention and achieves remarkable
progress. However, previous methods mainly rely on limited unimodal data (eg, RGB …