Related papers: Part Aware Contrastive Learning for Self-Supervise…

Advanced self-supervised visual representation learning methods rely on the instance discrimination (ID) pretext task. We point out that the ID task has an implicit semantic consistency (SC) assumption, which may not hold in unconstrained…

Molecular representation learning contributes to multiple downstream tasks such as molecular property prediction and drug design. To properly represent molecules, graph contrastive learning is a promising paradigm as it utilizes…

Contrastive learning has achieved great success in self-supervised visual representation learning, but existing approaches mostly ignored spatial information which is often crucial for visual representation. This paper presents…

3D skeleton-based action recognition (3D SAR) has gained significant attention within the computer vision community, owing to the inherent advantages offered by skeleton data. As a result, a plethora of impressive works, including those…

The popularity of self-supervised learning has made it possible to train models without relying on labeled data, which saves expensive annotation costs. However, most existing self-supervised contrastive learning methods often overlook the…

Skeleton-based human action recognition aims to classify human skeletal sequences, which are spatiotemporal representations of actions, into predefined categories. To reduce the reliance on costly annotations of skeletal sequences while…

A key requirement for the success of supervised deep learning is a large labeled dataset - a condition that is difficult to meet in medical image analysis. Self-supervised learning (SSL) can help in this regard by providing a strategy to…

Recent advances in self-supervised learning have attracted significant attention from both machine learning and neuroscience. This is primarily because self-supervised methods do not require annotated supervisory information, making them…

Recently, transformers have demonstrated great potential for modeling long-term dependencies from skeleton sequences and thereby gained ever-increasing attention in skeleton action recognition. However, the existing transformer-based…

In this work, we present Multi-Level Contrastive Learning for Dense Prediction Task (MCL), an efficient self-supervised method for learning region-level feature representation for dense prediction tasks. Our method is motivated by the three…

Human action recognition as an important application of computer vision has been studied for decades. Among various approaches, skeleton-based methods recently attract increasing attention due to their robust and superior performance.…

This paper presents a novel mid-level representation for action recognition, named spatio-temporal aware non-negative component representation (STANNCR). The proposed STANNCR is based on action component and incorporates the…

3D deep learning is a growing field of interest due to the vast amount of information stored in 3D formats. Triangular meshes are an efficient representation for irregular, non-uniform 3D objects. However, meshes are often challenging to…

Sequential recommendation (SR) aims to predict the subsequent behaviors of users by understanding their successive historical behaviors. Recently, some methods for SR are devoted to alleviating the data sparsity problem (i.e., limited…

Typically, objects with the same semantics are not always prominent in images containing different backgrounds. Motivated by this observation that accurately salient object detection is related to both foreground and background, we proposed…

Graph representation learning has attracted a surge of interest recently, whose target at learning discriminant embedding for each node in the graph. Most of these representation methods focus on supervised learning and heavily depend on…

Self-supervised learning (SSL) has emerged as a powerful paradigm for Chest X-ray (CXR) analysis under limited annotations. Yet, existing SSL strategies remain suboptimal for medical imaging. Masked image modeling allocates substantial…

As a pioneering work, PointContrast conducts unsupervised 3D representation learning via leveraging contrastive learning over raw RGB-D frames and proves its effectiveness on various downstream tasks. However, the trend of large-scale…

Semi-supervised learning acts as an effective way to leverage massive unlabeled data. In this paper, we propose a novel training strategy, termed as Semi-supervised Contrastive Learning (SsCL), which combines the well-known contrastive loss…

Mental disorder populations exhibit pronounced heterogeneity -- that is, the significant differences between samples -- poses a significant challenge to the definition of positive pairs in contrastive learning. To address this, we propose a…