Domain adaptation (DA) aims to alleviate the domain shift between source...
Accurate semantic segmentation models typically require significant
comp...
In this paper we propose a generative adversarial network (GAN) framewor...
Neural video compression has emerged as a novel paradigm combining train...
Computer vision has established a foothold in the online fashion retail
...
In this paper, we propose a deformable convolution-based generative
adve...
Data-driven paradigms using machine learning are becoming ubiquitous in ...
Most meta-learning approaches assume the existence of a very large set o...
Human beings learn and accumulate hierarchical knowledge over their life...
Domain adaptation (DA) aims to alleviate the domain shift between source...
Video compression benefits from advanced chroma intra prediction methods...
Recent years have witnessed the significant development of learning-base...
Domain adaptation (DA) aims to transfer the knowledge learned from a sou...
Online continual learning aims to learn from a non-IID stream of data fr...
GANs largely increases the potential impact of generative models. Theref...
Neural image compression (NIC) is a new coding paradigm where coding
cap...
Multimodal representations and continual learning are two areas closely
...
Neural image compression leverages deep neural networks to outperform
tr...
Zero-shot learning (ZSL) aims to discriminate images from unseen classes...
Unsupervised domain adaptation (UDA) aims to transfer the knowledge lear...
We propose bookworm continual learning(BCL), a flexible setting where un...
Zero-shot learning (ZSL) aims to discriminate images from unseen classes...
Modern computer vision requires processing large amounts of data, both w...
Humans are capable of learning new tasks without forgetting previous one...
Class-incremental learning of deep networks sequentially increases the n...
Variable rate is a requirement for flexible and adaptable image and vide...
One of the attractive characteristics of deep neural networks is their
a...
Recently, image-to-image translation research has witnessed remarkable
p...
The task of unpaired image-to-image translation is highly challenging du...
In recent years, convolutional neural networks (CNNs) have achieved
impr...
This paper addresses the problem of inferring unseen cross-domain and
cr...
A family of recent successful approaches to few-shot learning relies on
...
Deep convolutional networks (CNN) can achieve impressive results on RGB ...
Previous works on sequential learning address the problem of forgetting ...
This paper describes the multimodal Neural Machine Translation systems
d...
Transferring the knowledge of pretrained networks to new domains by mean...
We address the problem of image translation between domains or modalitie...
In this paper we propose an approach to avoiding catastrophic forgetting...
The central role of food in our individual and social life, combined wit...
Since scenes are composed in part of objects, accurate recognition of sc...
Scene recognition with RGB images has been extensively studied and has
r...
Deep Neural Networks trained on large datasets can be easily transferred...
This paper describes the monomodal and multimodal Neural Machine Transla...