Related papers: Skeleton Prototype Contrastive Learning with Multi…
Despite recent success on 2D human pose estimation, 3D human pose estimation still remains an open problem. A key challenge is the ill-posed depth ambiguity nature. This paper presents a novel intermediate feature representation named…
While the celebrated graph neural networks yield effective representations for individual nodes of a graph, there has been relatively less success in extending to the task of graph similarity learning. Recent work on graph similarity…
Visible-infrared person re-identification (VI Re-ID) aims to match person images between the visible and infrared modalities. Existing VI Re-ID methods mainly focus on extracting homogeneous structural relationships in an image, i.e. the…
Group Re-identification (G-ReID) faces greater complexity than individual Re-identification (ReID) due to challenges like mutual occlusion, dynamic member interactions, and evolving group structures. Prior graph-based approaches have aimed…
With large-scale well-labeled datasets, deep learning has shown significant success in medical image segmentation. However, it is challenging to acquire abundant annotations in clinical practice due to extensive expertise requirements and…
Graph Self-Supervised Learning (GSSL) has emerged as a powerful paradigm for generating high-quality representations for graph-structured data. While multi-scale graph contrastive learning has received increasing attention, many existing…
Person re-identification (person Re-Id) aims to retrieve the pedestrian images of a same person that captured by disjoint and non-overlapping cameras. Lots of researchers recently focuse on this hot issue and propose deep learning based…
In this paper, we focus on the semi-supervised person re-identification (Re-ID) case, which only has the intra-camera (within-camera) labels but not inter-camera (cross-camera) labels. In real-world applications, these intra-camera labels…
Heterogeneous graphs (HGs) are composed of multiple types of nodes and edges, making it more effective in capturing the complex relational structures inherent in the real world. However, in real-world scenarios, labeled data is often…
Graph-based models have emerged as a powerful paradigm for modeling multimodal urban data and learning region representations for various downstream tasks. However, existing approaches face two major limitations. (1) They typically employ…
In recent years, self-supervised representation learning for skeleton-based action recognition has been developed with the advance of contrastive learning methods. The existing contrastive learning methods use normal augmentations to…
Semi-supervised learning has demonstrated great potential in medical image segmentation by utilizing knowledge from unlabeled data. However, most existing approaches do not explicitly capture high-level semantic relations between distant…
High annotation costs are a substantial bottleneck in applying modern deep learning architectures to clinically relevant medical use cases, substantiating the need for novel algorithms to learn from unlabeled data. In this work, we propose…
In recent years, contrastive learning has drawn significant attention as an effective approach to reducing reliance on labeled data. However, existing methods for self-supervised skeleton-based action recognition still face three major…
Matching individuals across non-overlapping camera networks, known as person re-identification, is a fundamentally challenging problem due to the large visual appearance changes caused by variations of viewpoints, lighting, and occlusion.…
Recent years have witnessed the remarkable progress of applying deep learning models in video person re-identification (Re-ID). A key factor for video person Re-ID is to effectively construct discriminative and robust video feature…
Video-based person re-identification aims to match pedestrians from video sequences across non-overlapping camera views. The key factor for video person re-identification is to effectively exploit both spatial and temporal clues from video…
In recent years, supervised person re-identification (re-ID) models have received increasing studies. However, these models trained on the source domain always suffer dramatic performance drop when tested on an unseen domain. Existing…
Dynamics of human body skeletons convey significant information for human action recognition. Conventional approaches for modeling skeletons usually rely on hand-crafted parts or traversal rules, thus resulting in limited expressive power…
3D Skeleton-based human action recognition has attracted increasing attention in recent years. Most of the existing work focuses on supervised learning which requires a large number of labeled action sequences that are often expensive and…