Continuous unsupervised representation learning (CURL) research has grea...
Unsupervised contrastive learning methods have recently seen significant...
Person Re-identification (ReID) plays a more and more crucial role in re...
Objectives: Approximately 30
(ASCC) patients will experience recurrence ...
The principle underlying most existing continual learning (CL) methods i...
Unsupervised domain adaptive person re-identification (Re-ID) methods
al...
State-of-the-art deep neural networks are trained with large amounts
(mi...
We hypothesize that large language models (LLMs) based on the transforme...
Traditional federated learning uses the number of samples to calculate t...
Limited labeled data makes it hard to train models from scratch in medic...
Networked control systems are closed-loop feedback control systems conta...
Whole-body biometric recognition is an important area of research due to...
Bipartite graphs model relationships between two different sets of entit...
In this paper we describe a learned method of traffic scene generation
d...
Replay-based methods have proved their effectiveness on online continual...
Image translation has wide applications, such as style transfer and moda...
We study Graph Neural Networks (GNNs)-based embedding techniques for
kno...
Advanced science and technology provide a wealth of big data from differ...
Recently, CLIP-guided image synthesis has shown appealing performance on...
In this paper, we follow a data-centric philosophy and propose a novel m...
Certain tasks such as determining whether a given integer can be divided...
The unlearning problem of deep learning models, once primarily an academ...
As one of the most fundamental techniques in multimodal learning, cross-...
Self-supervised learning has recently emerged as a strong alternative in...
Continual learning (CL) can help pre-trained vision-language models
effi...
Data pruning aims to obtain lossless performances as training on the ori...
Dataset distillation reduces the network training cost by synthesizing s...
Dataset distillation aims to generate small datasets with little informa...
Information cascade in online social networks can be rather negative, e....
Very unhealthy air quality is consistently connected with numerous disea...
Pretrained language models such as Bidirectional Encoder Representations...
The power of Deep Neural Networks (DNNs) depends heavily on the training...
Automated radiology report generation aims at automatically generating a...
The recent advances in diffusion models have set an impressive milestone...
In this paper, we study \xw{dataset distillation (DD)}, from a novel
per...
Industrial recommender systems usually employ multi-source data to impro...
Rice is one of the main staple food in many areas of the world. The qual...
Lifelong object re-identification incrementally learns from a stream of
...
Self-supervised learning has been widely applied to train high-quality v...
Prediction uncertainty estimation has clinical significance as it can
po...
Successful point cloud registration relies on accurate correspondences
e...
For Head and Neck Cancers (HNC) patient management, automatic gross tumo...
Lossless and near-lossless image compression is of paramount importance ...
Though vision transformers (ViTs) have exhibited impressive ability for
...
Matchmaking systems are vital for creating fair matches in online multip...
In this paper, we investigate open-set recognition with domain
shift, wh...
Skeleton-based action recognition methods are limited by the semantic
ex...
Effectively integrating multi-scale information is of considerable
signi...
Restless multi-armed bandits (RMABs) extend multi-armed bandits to allow...
Domain Adaptation of Black-box Predictors (DABP) aims to learn a model o...