Transformer for skeleton-based action recognition: A review of recent advances
Skeleton-based action recognition has rapidly become one of the most popular and
essential research topics in computer vision. The task is to analyze the characteristics of …
essential research topics in computer vision. The task is to analyze the characteristics of …
Deep contrastive representation learning with self-distillation
Recently, contrastive learning (CL) is a promising way of learning discriminative
representations from time series data. In the representation hierarchy, semantic information …
representations from time series data. In the representation hierarchy, semantic information …
On the use of deep learning for video classification
The video classification task has gained significant success in the recent years. Specifically,
the topic has gained more attention after the emergence of deep learning models as a …
the topic has gained more attention after the emergence of deep learning models as a …
Dynamic dense graph convolutional network for skeleton-based human motion prediction
Graph Convolutional Networks (GCN) which typically follows a neural message passing
framework to model dependencies among skeletal joints has achieved high success in …
framework to model dependencies among skeletal joints has achieved high success in …
Self-supervised graph-level representation learning with adversarial contrastive learning
The recently developed unsupervised graph representation learning approaches apply
contrastive learning into graph-structured data and achieve promising performance …
contrastive learning into graph-structured data and achieve promising performance …
Neighbor-guided consistent and contrastive learning for semi-supervised action recognition
Semi-supervised learning has been well established in the area of image classification but
remains to be explored in video-based action recognition. FixMatch is a state-of-the-art semi …
remains to be explored in video-based action recognition. FixMatch is a state-of-the-art semi …
Self-supervised 3D action representation learning with skeleton cloud colorization
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 …
years. Most of the existing work focuses on supervised learning which requires a large …
Msvit: training multiscale vision transformers for image retrieval
The recently developed vision transformer (ViT) has achieved promising results on image
retrieval compared to convolutional neural networks. However, most of these vision …
retrieval compared to convolutional neural networks. However, most of these vision …
Individual and structural graph information bottlenecks for out-of-distribution generalization
Out-of-distribution (OOD) graph generalization are critical for many real-world applications.
Existing methods neglect to discard spurious or noisy features of inputs, which are irrelevant …
Existing methods neglect to discard spurious or noisy features of inputs, which are irrelevant …
Sptr: Structure-preserving transformer for unsupervised indoor depth completion
Recovering a dense depth map from a pair of indoor RGB and sparse depth images in an
unsupervised manner is paramount in applications such as autonomous driving and 3D …
unsupervised manner is paramount in applications such as autonomous driving and 3D …