Referring video object segmentation (RVOS), as a supervised learning tas...
The way we analyse clinical texts has undergone major changes over the l...
Pre-trained vision-language models, e.g., CLIP, working with manually
de...
This paper strives for domain generalization, where models are trained
e...
Few-shot meta-learning presents a challenge for gradient descent optimiz...
Meta-learning algorithms are able to learn a new task using previously
l...
Recently, Transformers have emerged as the go-to architecture for both v...
Modern image classifiers perform well on populated classes, while degrad...
Image super-resolution (SR) has attracted increasing attention due to it...
The channel attention mechanism is a useful technique widely employed in...
Multimodal few-shot learning is challenging due to the large domain gap
...
In this paper, we propose energy-based sample adaptation at test time fo...
The task of multimodal referring expression comprehension (REC), aiming ...
We aim for source-free domain adaptation, where the task is to deploy a ...
Medical image datasets and their annotations are not growing as fast as ...
In this paper, we focus on multi-task classification, where related
clas...
Deep learning models have shown a great effectiveness in recognition of
...
The photographs captured by digital cameras usually suffer from over-exp...
We strive to learn a model from a set of source domains that generalizes...
Kernel continual learning by <cit.> has recently
emerged as a strong con...
Neural memory enables fast adaptation to new tasks with just a few train...
Neural processes have recently emerged as a class of powerful neural lat...
Multi-task learning aims to explore task relatedness to improve individu...
Annotation burden has become one of the biggest barriers to semantic
seg...
Automating report generation for medical imaging promises to reduce work...
This paper introduces kernel continual learning, a simple but effective
...
A critical challenge faced by supervised word sense disambiguation (WSD)...
This paper aims to address few-shot semantic segmentation. While existin...
Domain generalization is challenging due to the domain shift and the
unc...
Few-shot learning deals with the fundamental and challenging problem of
...
Disease classification relying solely on imaging data attracts great int...
The Cobb angle that quantitatively evaluates the spinal curvature plays ...
In this paper, we introduce variational semantic memory into meta-learni...
Domain generalization models learn to generalize to previously unseen
do...
In this work, we introduce kernels with random Fourier features in the
m...
In this work, we present an end-to-end framework to settle data associat...
Crowd counting has recently attracted increasing interest in computer vi...
In this paper, we present a two-stream multi-task network for fashion
re...
Being able to track an anonymous object, a model-free tracker is
compreh...
Crowd counting usually addressed by density estimation becomes an
increa...
Representation learning is a fundamental but challenging problem, especi...