Related papers: Squeeze-and-Excitation on Spatial and Temporal Dee…

Human motion prediction aims to generate future motions based on the observed human motions. Witnessing the success of Recurrent Neural Networks (RNN) in modeling the sequential data, recent works utilize RNN to model human-skeleton motion…

Skeleton-based action recognition is a central task in computer vision and human-robot interaction. However, most previous methods suffer from overlooking the explicit exploitation of the latent data distributions (i.e., the intra-class…

Spiking Neural Networks (SNNs), as one of the algorithmic models in neuromorphic computing, have gained a great deal of research attention owing to temporal information processing capability, low power consumption, and high biological…

Fine-grained visual recognition typically depends on modeling subtle difference from object parts. However, these parts often exhibit dramatic visual variations such as occlusions, viewpoints, and spatial transformations, making it hard to…

Spatiotemporal graph convolutional networks (STGCNs) have emerged as a desirable model for skeleton-based human action recognition. Despite achieving state-of-the-art performance, there is a limited understanding of the representations…

Skeleton-based action recognition relies on the extraction of spatial-temporal topological information. Hypergraphs can establish prior unnatural dependencies for the skeleton. However, the existing methods only focus on the construction of…

Human actions in video sequences are characterized by the complex interplay between spatial features and their temporal dynamics. In this paper, we propose novel tensor representations for compactly capturing such higher-order relationships…

Skeleton-based action recognition has achieved remarkable results in human action recognition with the development of graph convolutional networks (GCNs). However, the recent works tend to construct complex learning mechanisms with…

Convolutional neural networks learns spatial features and are heavily interlinked within kernels. The SE module have broken the traditional route of neural networks passing the entire result to next layer. Instead SE only passes important…

Deep Learning based techniques have gained significance over the past few years in the field of medicine. They are used in various applications such as classifying medical images, segmentation and identification. The existing architectures…

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…

There has been a dramatic increase in the volume of videos and their related content uploaded to the internet. Accordingly, the need for efficient algorithms to analyse this vast amount of data has attracted significant research interest.…

Spatial-temporal graph convolutional networks (ST-GCNs) showcase impressive performance in skeleton-based human action recognition (HAR). However, despite the development of numerous models, their recognition performance does not differ…

Spatio-temporal feature learning is of central importance for action recognition in videos. Existing deep neural network models either learn spatial and temporal features independently (C2D) or jointly with unconstrained parameters (C3D).…

Human Activity Recognition (HAR) using wearable sensor data has become a central task in mobile computing, healthcare, and human-computer interaction. Despite the success of traditional deep learning models such as CNNs and RNNs, they often…

Human motion prediction is an important and challenging task in many computer vision application domains. Recent work concentrates on utilizing the timing processing ability of recurrent neural networks (RNNs) to achieve smooth and reliable…

Pose based hand gesture recognition has been widely studied in the recent years. Compared with full body action recognition, hand gesture involves joints that are more spatially closely distributed with stronger collaboration. This nature…

In this paper, we study the effect of introducing channel and spatial attention mechanisms, namely SEN-Net, ECA-Net, and CBAM, to existing CNN vision-based models such as VGGNet, ResNet, and ResNetV2 to perform the Facial Emotion…

As a unique and promising biometric, video-based gait recognition has broad applications. The key step of this methodology is to learn the walking pattern of individuals, which, however, often suffers challenges to extract the behavioral…

Spatio-temporal representations in frame sequences play an important role in the task of action recognition. Previously, a method of using optical flow as a temporal information in combination with a set of RGB images that contain spatial…