Multi-scale structural graph convolutional network for skeleton-based action recognition

S Jang, H Lee, WJ Kim, J Lee, S Woo… - IEEE Transactions on …, 2024‏ - ieeexplore.ieee.org
Graph convolutional networks (GCNs) have attracted considerable interest in skeleton-
based action recognition. Existing GCN-based models have proposed methods to learn …

Learning contrastive self-distillation for ultra-fine-grained visual categorization targeting limited samples

Z Fang, X Jiang, H Tang, Z Li - IEEE Transactions on Circuits …, 2024‏ - ieeexplore.ieee.org
In the field of intelligent multimedia analysis, ultra-fine-grained visual categorization (Ultra-
FGVC) plays a vital role in distinguishing intricate subcategories within broader categories …

Self-adaptive graph with nonlocal attention network for skeleton-based action recognition

C Pang, X Gao, Z Chen, L Lyu - IEEE Transactions on Neural …, 2023‏ - ieeexplore.ieee.org
Graph convolutional networks (GCNs) have achieved encouraging progress in modeling
human body skeletons as spatial–temporal graphs. However, existing methods still suffer …

Hierarchical aggregated graph neural network for skeleton-based action recognition

P Geng, X Lu, W Li, L Lyu - IEEE Transactions on Multimedia, 2024‏ - ieeexplore.ieee.org
Supervised human action recognition methods based on skeleton data have achieved
impressive performance recently. However, many current works emphasize the design of …

MIGA-Net: Multi-view image information learning based on graph attention network for SAR target recognition

R Wang, T Su, D Xu, J Chen… - IEEE Transactions on …, 2024‏ - ieeexplore.ieee.org
Neural networks for synthetic aperture radar (SAR) automatic target recognition often
encounter overfitting challenges owing to limited training samples. Moreover, the azimuth …

Seeking False Hard Negatives for Graph Contrastive Learning

X Liu, B Qian, H Liu, D Guo, Y Wang… - IEEE Transactions on …, 2024‏ - ieeexplore.ieee.org
Graph Contrastive Learning (GCL) has achieved great success in self-supervised
representation learning throughout positive and negative pairs based on graph neural …

Discriminative segment focus network for fine-grained video action recognition

B Sun, X Ye, T Yan, Z Wang, H Li, Z Wang - ACM Transactions on …, 2024‏ - dl.acm.org
Fine-grained video action recognition aims at identifying minor and discriminative variations
among fine categories of actions. While many recent action recognition methods have been …

Skeleton-based action recognition through attention guided heterogeneous graph neural network

T Li, P Geng, X Lu, W Li, L Lyu - Knowledge-Based Systems, 2025‏ - Elsevier
Previous graph convolutional networks typically use homogeneous graphs to explore the
hidden dependencies between joints in skeleton-based action recognition. Consequently …

Variation-aware directed graph convolutional networks for skeleton-based action recognition

T Li, P Geng, G Cai, X Hou, X Lu, L Lyu - Knowledge-Based Systems, 2024‏ - Elsevier
Abstract Directed Graph convolutional networks (DGCNs) have been indeed gaining
attention and being applied in skeleton-based action recognition tasks to capture the …

DSDC-GCN: Decoupled Static-Dynamic Co-occurrence Graph Convolutional Networks for Skeleton-Based Action Recognition

T Zhuang, Z Qin, Y Ding, Z Qin, J Geng… - … on Circuits and …, 2024‏ - ieeexplore.ieee.org
The existing approaches for skeleton-based action recognition based on graph
convolutional networks (GCNs) primarily emphasize the construction of human skeletal …