Developing GCN: Graph Convolutional Network with Evolving Parameters for Dynamic Graphs

2021 ◽  
pp. 369-376
Author(s):  
Lin Lan ◽  
Jin li ◽  
Yang-Geng Fu
Keyword(s):  
Dynamic Graphs ◽  
Convolutional Network

scholarly journals DGCN: Dynamic Graph Convolutional Network for Efficient Multi-Person Pose Estimation

2020 ◽  
Vol 34 (07) ◽  
pp. 11924-11931
Author(s):  
Zhongwei Qiu ◽  
Kai Qiu ◽  
Jianlong Fu ◽  
Dongmei Fu
Keyword(s):  
Pose Estimation ◽  
State Of The Art ◽  
Semantic Relations ◽  
Dynamic Graphs ◽  
Dynamic Graph ◽  
Convolutional Network ◽  
Bottom Up ◽  
Multi Level ◽  
Human Pose ◽  
Relative Gains

Multi-person pose estimation aims to detect human keypoints from images with multiple persons. Bottom-up methods for multi-person pose estimation have attracted extensive attention, owing to the good balance between efficiency and accuracy. Recent bottom-up methods usually follow the principle of keypoints localization and grouping, where relations between keypoints are the keys to group keypoints. These relations spontaneously construct a graph of keypoints, where the edges represent the relations between two nodes (i.e., keypoints). Existing bottom-up methods mainly define relations by empirically picking out edges from this graph, while omitting edges that may contain useful semantic relations. In this paper, we propose a novel Dynamic Graph Convolutional Module (DGCM) to model rich relations in the keypoints graph. Specifically, we take into account all relations (all edges of the graph) and construct dynamic graphs to tolerate large variations of human pose. The DGCM is quite lightweight, which allows it to be stacked like a pyramid architecture and learn structural relations from multi-level features. Our network with single DGCM based on ResNet-50 achieves relative gains of 3.2% and 4.8% over state-of-the-art bottom-up methods on COCO keypoints and MPII dataset, respectively.

scholarly journals K-Core based Temporal Graph Convolutional Network for Dynamic Graphs

2020 ◽  
pp. 1-1
Author(s):  
Jingxin Liu ◽  
Chang Xu ◽  
Chang Yin ◽  
Weiqiang Wu ◽  
You Song
Keyword(s):  
Dynamic Graphs ◽  
Convolutional Network ◽  
Temporal Graph

scholarly journals AddGraph: Anomaly Detection in Dynamic Graph Using Attention-based Temporal GCN

2019 ◽  
Author(s):  
Li Zheng ◽  
Zhenpeng Li ◽  
Jian Li ◽  
Zhao Li ◽  
Jun Gao
Keyword(s):  
Anomaly Detection ◽  
Dynamic Graphs ◽  
Dynamic Graph ◽  
Short Term ◽  
Convolutional Network ◽  
Attention Model ◽  
Temporal Features ◽  
Structural Content ◽  
Real World Datasets

Anomaly detection in dynamic graphs becomes very critical in many different application scenarios, e.g., recommender systems, while it also raises huge challenges due to the high flexible nature of anomaly and lack of sufficient labelled data. It is better to learn the anomaly patterns by considering all possible features including the structural, content and temporal features, rather than utilizing heuristic rules over the partial features. In this paper, we propose AddGraph, a general end-to-end anomalous edge detection framework using an extended temporal GCN (Graph Convolutional Network) with an attention model, which can capture both long-term patterns and the short-term patterns in dynamic graphs. In order to cope with insufficient explicit labelled data, we employ the negative sampling and margin loss in training of AddGraph in a semi-supervised fashion. We conduct extensive experiments on real-world datasets, and illustrate that AddGraph can outperform the state-of-the-art competitors in anomaly detection significantly.

scholarly journals Knowledge and Geo-Object Based Graph Convolutional Network for Remote Sensing Semantic Segmentation

Sensors ◽  
2021 ◽  
Vol 21 (11) ◽  
pp. 3848
Author(s):  
Wei Cui ◽  
Meng Yao ◽  
Yuanjie Hao ◽  
Ziwei Wang ◽  
Xin He ◽  
...  
Keyword(s):  
Remote Sensing ◽  
Prior Knowledge ◽  
Contextual Information ◽  
Information Aggregation ◽  
Semantic Segmentation ◽  
Spatial Correlations ◽  
Convolutional Network ◽  
Object Based ◽  
Graph Neural Networks ◽  
Salt And Pepper

Pixel-based semantic segmentation models fail to effectively express geographic objects and their topological relationships. Therefore, in semantic segmentation of remote sensing images, these models fail to avoid salt-and-pepper effects and cannot achieve high accuracy either. To solve these problems, object-based models such as graph neural networks (GNNs) are considered. However, traditional GNNs directly use similarity or spatial correlations between nodes to aggregate nodes’ information, which rely too much on the contextual information of the sample. The contextual information of the sample is often distorted, which results in a reduction in the node classification accuracy. To solve this problem, a knowledge and geo-object-based graph convolutional network (KGGCN) is proposed. The KGGCN uses superpixel blocks as nodes of the graph network and combines prior knowledge with spatial correlations during information aggregation. By incorporating the prior knowledge obtained from all samples of the study area, the receptive field of the node is extended from its sample context to the study area. Thus, the distortion of the sample context is overcome effectively. Experiments demonstrate that our model is improved by 3.7% compared with the baseline model named Cluster GCN and 4.1% compared with U-Net.

scholarly journals SACN: A Novel Rotating Face Detector Based on Architecture Search

Electronics ◽  
2021 ◽  
Vol 10 (5) ◽  
pp. 558
Author(s):  
Anping Song ◽  
Xiaokang Xu ◽  
Xinyi Zhai
Keyword(s):  
Face Detection ◽  
Human Face ◽  
Angle Error ◽  
Rotation Invariant ◽  
Convolutional Network ◽  
Data Set ◽  
Practical Applications ◽  
Model Size ◽  
Average Angle ◽  
Face Detector

Rotation-Invariant Face Detection (RIPD) has been widely used in practical applications; however, the problem of the adjusting of the rotation-in-plane (RIP) angle of the human face still remains. Recently, several methods based on neural networks have been proposed to solve the RIP angle problem. However, these methods have various limitations, including low detecting speed, model size, and detecting accuracy. To solve the aforementioned problems, we propose a new network, called the Searching Architecture Calibration Network (SACN), which utilizes architecture search, fully convolutional network (FCN) and bounding box center cluster (CC). SACN was tested on the challenging Multi-Oriented Face Detection Data Set and Benchmark (MOFDDB) and achieved a higher detecting accuracy and almost the same speed as existing detectors. Moreover, the average angle error is optimized from the current 12.6° to 10.5°.

scholarly journals NPU RGB+D Dataset and a Feature-Enhanced LSTM-DGCN Method for Action Recognition of Basketball Players

2021 ◽  
Vol 11 (10) ◽  
pp. 4426
Author(s):  
Chunyan Ma ◽  
Ji Fan ◽  
Jinghao Yao ◽  
Tao Zhang
Keyword(s):  
Action Recognition ◽  
Large Scale ◽  
Short Term Memory ◽  
Evaluation Criteria ◽  
Image Data ◽  
Basketball Player ◽  
Basketball Players ◽  
Convolutional Network ◽  
Atomic Actions ◽  
New Feature

Computer vision-based action recognition of basketball players in basketball training and competition has gradually become a research hotspot. However, owing to the complex technical action, diverse background, and limb occlusion, it remains a challenging task without effective solutions or public dataset benchmarks. In this study, we defined 32 kinds of atomic actions covering most of the complex actions for basketball players and built the dataset NPU RGB+D (a large scale dataset of basketball action recognition with RGB image data and Depth data captured in Northwestern Polytechnical University) for 12 kinds of actions of 10 professional basketball players with 2169 RGB+D videos and 75 thousand frames, including RGB frame sequences, depth maps, and skeleton coordinates. Through extracting the spatial features of the distances and angles between the joint points of basketball players, we created a new feature-enhanced skeleton-based method called LSTM-DGCN for basketball player action recognition based on the deep graph convolutional network (DGCN) and long short-term memory (LSTM) methods. Many advanced action recognition methods were evaluated on our dataset and compared with our proposed method. The experimental results show that the NPU RGB+D dataset is very competitive with the current action recognition algorithms and that our LSTM-DGCN outperforms the state-of-the-art action recognition methods in various evaluation criteria on our dataset. Our action classifications and this NPU RGB+D dataset are valuable for basketball player action recognition techniques. The feature-enhanced LSTM-DGCN has a more accurate action recognition effect, which improves the motion expression ability of the skeleton data.

Sign in / Sign up

Export Citation Format

Share Document