Although deep learning algorithms have achieved significant progress in a variety of
domains, they require costly annotations on huge datasets. Self-supervised learning (SSL) …

Negative sampling has swiftly risen to prominence as a focal point of research, with wide-
ranging applications spanning machine learning, computer vision, natural language …

Current semantic segmentation methods focus only on mining" local" context, ie,
dependencies between pixels within individual images, by context-aggregation modules …

Transformers and masked language modeling are quickly being adopted and explored in
computer vision as vision transformers and masked image modeling (MIM). In this work, we …

The wide application of smart devices enables the availability of multimodal data, which can
be utilized in many tasks. In the field of multimodal sentiment analysis, most previous works …

This work studies the problem of image semantic segmentation. Current approaches focus
mainly on mining “local” context, ie, dependencies between pixels within individual images …

This study reveals the inherent tolerance of contrastive learning (CL) towards sampling bias,
wherein negative samples may encompass similar semantics (\eg labels). However, existing …

Despite great improvements in semantic segmentation challenges persist because of the
lack of local/global contexts and the relationship between them. In this paper we propose …

Recent self-supervised representation learning techniques have largely closed the gap
between supervised and unsupervised learning on ImageNet classification. While the …

Learning universal time series representations applicable to various types of downstream
tasks is challenging but valuable in real applications. Recently, researchers have attempted …