Related papers: Self-Attention Network for Skeleton-based Human Ac…

While originally designed for natural language processing tasks, the self-attention mechanism has recently taken various computer vision areas by storm. However, the 2D nature of images brings three challenges for applying self-attention in…

Current state-of-the-art approaches for spatio-temporal action localization rely on detections at the frame level and model temporal context with 3D ConvNets. Here, we go one step further and model spatio-temporal relations to capture the…

In recent years, Generative Adversarial Networks (GAN) have emerged as a powerful method for learning the mapping from noisy latent spaces to realistic data samples in high-dimensional space. So far, the development and application of GANs…

Despite the notable progress made in action recognition tasks, not much work has been done in action recognition specifically for human-robot interaction. In this paper, we deeply explore the characteristics of the action recognition task…

Graph convolutional networks have been widely used for skeleton-based action recognition due to their excellent modeling ability of non-Euclidean data. As the graph convolution is a local operation, it can only utilize the short-range joint…

Skeleton-based action recognition has gained significant attention for its ability to efficiently represent spatiotemporal information in a lightweight format. Most existing approaches use graph-based models to process skeleton sequences,…

Graph convolution networks (GCN) have been widely used in skeleton-based action recognition. We note that existing GCN-based approaches primarily rely on prescribed graphical structures (ie., a manually defined topology of skeleton joints),…

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…

Reliable segmentation of retinal vessels can be employed as a way of monitoring and diagnosing certain diseases, such as diabetes and hypertension, as they affect the retinal vascular structure. In this work, we propose the Residual Spatial…

Effective processing of video input is essential for the recognition of temporally varying events such as human actions. Motivated by the often distinctive temporal characteristics of actions in either horizontal or vertical direction, we…

Automatic human action recognition is indispensable for almost artificial intelligent systems such as video surveillance, human-computer interfaces, video retrieval, etc. Despite a lot of progress, recognizing actions in an unknown video is…

Graph Convolutional Networks (GCNs) have been widely used in skeleton-based human action recognition. In GCN-based methods, the spatio-temporal graph is fundamental for capturing motion patterns. However, existing approaches ignore the…

We propose a novel skeleton-based representation for 3D action recognition in videos using Deep Convolutional Neural Networks (D-CNNs). Two key issues have been addressed: First, how to construct a robust representation that easily captures…

Graph Convolutional Networks (GCNs) have attracted increasing interests for the task of skeleton-based action recognition. The key lies in the design of the graph structure, which encodes skeleton topology information. In this paper, we…

It is difficult for people to interpret the decision-making in the inference process of deep neural networks. Visual explanation is one method for interpreting the decision-making of deep learning. It analyzes the decision-making of 2D CNNs…

Accurate assessment of patient actions plays a crucial role in healthcare as it contributes significantly to disease progression monitoring and treatment effectiveness. However, traditional approaches to assess patient actions often rely on…

Joint segmentation and classification of fine-grained actions is important for applications of human-robot interaction, video surveillance, and human skill evaluation. However, despite substantial recent progress in large-scale action…

The self-supervised pretraining paradigm has achieved great success in learning 3D action representations for skeleton-based action recognition using contrastive learning. However, learning effective representations for skeleton-based…

In this paper, we focus on the spatio-temporal aspect of recognizing Activities of Daily Living (ADL). ADL have two specific properties (i) subtle spatio-temporal patterns and (ii) similar visual patterns varying with time. Therefore, ADL…

Spatio-temporal information is key to resolve occlusion and depth ambiguity in 3D pose estimation. Previous methods have focused on either temporal contexts or local-to-global architectures that embed fixed-length spatio-temporal…