CoSign: Exploring co-occurrence signals in skeleton-based continuous sign language recognition

P Jiao, Y Min, Y Li, X Wang, L Lei… - Proceedings of the …, 2023‏ - openaccess.thecvf.com
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 …

Multi-modality co-learning for efficient skeleton-based action recognition

J Liu, C Chen, M Liu - Proceedings of the 32nd ACM International …, 2024‏ - dl.acm.org
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 …

BlockGCN: Redefine Topology Awareness for Skeleton-Based Action Recognition

Y Zhou, X Yan, ZQ Cheng, Y Yan… - Proceedings of the …, 2024‏ - openaccess.thecvf.com
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 …

Overcoming topology agnosticism: Enhancing skeleton-based action recognition through redefined skeletal topology awareness

Y Zhou, ZQ Cheng, JY He, B Luo, Y Geng… - arxiv preprint arxiv …, 2023‏ - arxiv.org
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 …

SMART-vision: survey of modern action recognition techniques in vision

AK AlShami, R Rabinowitz, K Lam, Y Shleibik… - Multimedia Tools and …, 2024‏ - Springer
Abstract Human Action Recognition (HAR) is a challenging domain in computer vision,
involving recognizing complex patterns by analyzing the spatiotemporal dynamics of …

Mutual Information Driven Equivariant Contrastive Learning for 3D Action Representation Learning

L Lin, J Zhang, J Liu - IEEE Transactions on Image Processing, 2024‏ - ieeexplore.ieee.org
Self-supervised contrastive learning has proven to be successful for skeleton-based action
recognition. For contrastive learning, data transformations are found to fundamentally affect …

Spatial-Temporal Masked Autoencoder for Multi-Device Wearable Human Activity Recognition

S Miao, L Chen, R Hu - Proceedings of the ACM on Interactive, Mobile …, 2024‏ - dl.acm.org
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 …

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 …

ConvST-LSTM-Net: convolutional spatiotemporal LSTM networks for skeleton-based human action recognition

A Sharma, R Singh - International Journal of Multimedia Information …, 2023‏ - Springer
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 …

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 …