Local and Non-local Context Graph Convolutional Networks for Skeleton-Based Action Recognition

2021 ◽  
pp. 243-254
Author(s):  
Zikai Gao ◽  
Yang Zhao ◽  
Zhe Han ◽  
Kang Wang ◽  
Yong Dou
Keyword(s):  
Action Recognition ◽  
Local Context ◽  
Convolutional Networks ◽  
Non Local

Attention adjacency matrix based graph convolutional networks for skeleton-based action recognition

2021 ◽  
Vol 440 ◽  
pp. 230-239
Author(s):  
Jun Xie ◽  
Qiguang Miao ◽  
Ruyi Liu ◽  
Wentian Xin ◽  
Lei Tang ◽  
...  
Keyword(s):  
Action Recognition ◽  
Adjacency Matrix ◽  
Convolutional Networks

CyberEyes: Cybersecurity Entity Recognition Model Based on Graph Convolutional Network

2020 ◽  
Author(s):  
Yong Fang ◽  
Yuchi Zhang ◽  
Cheng Huang
Keyword(s):  
Complex Structure ◽  
Named Entity Recognition ◽  
Internet Technology ◽  
Entity Recognition ◽  
Local Context ◽  
Knowledge Graph ◽  
Convolutional Network ◽  
Evaluation Standard ◽  
Recognition Model ◽  
Non Local

Abstract Cybersecurity has gradually become the public focus between common people and countries with the high development of Internet technology in daily life. The cybersecurity knowledge analysis methods have achieved high evolution with the help of knowledge graph technology, especially a lot of threat intelligence information could be extracted with fine granularity. But named entity recognition (NER) is the primary task for constructing security knowledge graph. Traditional NER models are difficult to determine entities that have a complex structure in the field of cybersecurity, and it is difficult to capture non-local and non-sequential dependencies. In this paper, we propose a cybersecurity entity recognition model CyberEyes that uses non-local dependencies extracted by graph convolutional neural networks. The model can capture both local context and graph-level non-local dependencies. In the evaluation experiments, our model reached an F1 score of 90.28% on the cybersecurity corpus under the gold evaluation standard for NER, which performed better than the 86.49% obtained by the classic CNN-BiLSTM-CRF model.

scholarly journals Action Recognition via Pose-Based Graph Convolutional Networks with Intermediate Dense Supervision

2021 ◽  
pp. 108170
Author(s):  
Lei Shi ◽  
Yifan Zhang ◽  
Jian Cheng ◽  
Hanqing Lu
Keyword(s):  
Action Recognition ◽  
Convolutional Networks

Multi-stream slowFast graph convolutional networks for skeleton-based action recognition

2021 ◽  
Vol 109 ◽  
pp. 104141
Author(s):  
Ning Sun ◽  
Ling Leng ◽  
Jixin Liu ◽  
Guang Han
Keyword(s):  
Action Recognition ◽  
Convolutional Networks

Skeleton-based Action Recognition with Focusing-Diffusion Graph Convolutional Networks

2021 ◽  
pp. 1-1
Author(s):  
Jialin Gao ◽  
Tong He ◽  
Xi Zhou ◽  
Shiming Ge
Keyword(s):  
Action Recognition ◽  
Convolutional Networks

Forward-reverse Adaptive Graph Convolutional Networks for Skeleton-Based Action Recognition

2021 ◽  
Author(s):  
Zesheng Hu ◽  
Zihao Pan ◽  
Qiang Wang ◽  
Lei Yu ◽  
Shumin Fei
Keyword(s):  
Action Recognition ◽  
Convolutional Networks

scholarly journals Non-Local Context Encoder: Robust Biomedical Image Segmentation against Adversarial Attacks

2019 ◽  
Vol 33 ◽  
pp. 8417-8424 ◽  
Author(s):  
Xiang He ◽  
Sibei Yang ◽  
Guanbin Li ◽  
Haofeng Li ◽  
Huiyou Chang ◽  
...  
Keyword(s):  
Image Segmentation ◽  
State Of The Art ◽  
Contextual Information ◽  
Local Context ◽  
Deep Convolutional Neural Networks ◽  
Biomedical Image ◽  
Feature Representations ◽  
Segmentation Methods ◽  
Spatial Dependencies ◽  
Non Local

Recent progress in biomedical image segmentation based on deep convolutional neural networks (CNNs) has drawn much attention. However, its vulnerability towards adversarial samples cannot be overlooked. This paper is the first one that discovers that all the CNN-based state-of-the-art biomedical image segmentation models are sensitive to adversarial perturbations. This limits the deployment of these methods in safety-critical biomedical fields. In this paper, we discover that global spatial dependencies and global contextual information in a biomedical image can be exploited to defend against adversarial attacks. To this end, non-local context encoder (NLCE) is proposed to model short- and long-range spatial dependencies and encode global contexts for strengthening feature activations by channel-wise attention. The NLCE modules enhance the robustness and accuracy of the non-local context encoding network (NLCEN), which learns robust enhanced pyramid feature representations with NLCE modules, and then integrates the information across different levels. Experiments on both lung and skin lesion segmentation datasets have demonstrated that NLCEN outperforms any other state-of-the-art biomedical image segmentation methods against adversarial attacks. In addition, NLCE modules can be applied to improve the robustness of other CNN-based biomedical image segmentation methods.

Sign in / Sign up

Export Citation Format

Share Document