CoSign: Exploring co-occurrence signals in skeleton-based continuous sign language recognition
The co-occurrence signals (eg, hand shape, facial expression, and lip pattern) play a critical
role in Continuous Sign Language Recognition (CSLR). Compared to RGB data, skeleton …
role in Continuous Sign Language Recognition (CSLR). Compared to RGB data, skeleton …
Multi-modality co-learning for efficient skeleton-based action recognition
Skeleton-based action recognition has garnered significant attention due to the utilization of
concise and resilient skeletons. Nevertheless, the absence of detailed body information in …
concise and resilient skeletons. Nevertheless, the absence of detailed body information in …
BlockGCN: Redefine Topology Awareness for Skeleton-Based Action Recognition
Abstract Graph Convolutional Networks (GCNs) have long set the state-of-the-art in skeleton-
based action recognition leveraging their ability to unravel the complex dynamics of human …
based action recognition leveraging their ability to unravel the complex dynamics of human …
Overcoming topology agnosticism: Enhancing skeleton-based action recognition through redefined skeletal topology awareness
Graph Convolutional Networks (GCNs) have long defined the state-of-the-art in skeleton-
based action recognition, leveraging their ability to unravel the complex dynamics of human …
based action recognition, leveraging their ability to unravel the complex dynamics of human …
SMART-vision: survey of modern action recognition techniques in vision
Abstract Human Action Recognition (HAR) is a challenging domain in computer vision,
involving recognizing complex patterns by analyzing the spatiotemporal dynamics of …
involving recognizing complex patterns by analyzing the spatiotemporal dynamics of …
Mutual Information Driven Equivariant Contrastive Learning for 3D Action Representation Learning
Self-supervised contrastive learning has proven to be successful for skeleton-based action
recognition. For contrastive learning, data transformations are found to fundamentally affect …
recognition. For contrastive learning, data transformations are found to fundamentally affect …
Spatial-Temporal Masked Autoencoder for Multi-Device Wearable Human Activity Recognition
The widespread adoption of wearable devices has led to a surge in the development of multi-
device wearable human activity recognition (WHAR) systems. Nevertheless, the …
device wearable human activity recognition (WHAR) systems. Nevertheless, the …
VT-SGN: Spiking Graph Neural Network for Neuromorphic Visual-Tactile Fusion
P Wu, H Zhang, Y Li, W Chen… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Current issues with neuromorphic visual–tactile perception include limited training network
representation and inadequate cross-modal fusion. To address these two issues, we …
representation and inadequate cross-modal fusion. To address these two issues, we …
ConvST-LSTM-Net: convolutional spatiotemporal LSTM networks for skeleton-based human action recognition
Human action recognition (HAR) emphases on perceiving and identifying the action
behavior done by humans within an image/video. The HAR activities include motion patterns …
behavior done by humans within an image/video. The HAR activities include motion patterns …
Two-stream spatio-temporal GCN-transformer networks for skeleton-based action recognition
D Chen, M Chen, P Wu, M Wu, T Zhang, C Li - Scientific Reports, 2025 - nature.com
For the purpose of achieving accurate skeleton-based action recognition, the majority of
prior approaches have adopted a serial strategy that combines Graph Convolutional …
prior approaches have adopted a serial strategy that combines Graph Convolutional …