In this paper, we propose the K -Shot Contrastive Learning (KSCL) of visual features by applying multiple augmentations to investigate the sample variations within individual instances. It aims to …
Human motion prediction aims to generate future motions based on the observed human motions. Witnessing the success of Recurrent Neural Networks (RNN) in modeling sequential data, recent works util…
Representation learning with small labeled data have emerged in many problems, since the success of deep neural networks often relies on the availability of a huge amount of labeled data that is ex…
Transformation equivariant representations (TERs) aim to capture the intrinsic visual structures that equivary to various transformations by expanding the notion of translation equivariance underly…
Differentiable architecture search (DARTS) enables effective neural architecture search (NAS) using gradient descent, but suffers from high memory and computational costs. In this paper, we propose…