Hierarchical Graph Convolutional Network for Data Evaluation of Dynamic Graphs

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.

Download Full-text

PH-GCN: Person Retrieval with Part-based Hierarchical Graph Convolutional Network

IEEE Transactions on Multimedia ◽

10.1109/tmm.2021.3095789 ◽

2021 ◽

pp. 1-1

Author(s):

Bo Jiang ◽

Xixi Wang ◽

Aihua Zheng ◽

Jin Tang ◽

Bin Luo

Keyword(s):

Convolutional Network ◽

Hierarchical Graph

Download Full-text

Hierarchical Graph Convolutional Network for Skeleton-Based Action Recognition

Lecture Notes in Computer Science - Image and Graphics ◽

10.1007/978-3-030-34120-6_8 ◽

2019 ◽

pp. 93-102

Author(s):

Linjiang Huang ◽

Yan Huang ◽

Wanli Ouyang ◽

Liang Wang

Keyword(s):

Action Recognition ◽

Convolutional Network ◽

Hierarchical Graph

Download Full-text

K-Core based Temporal Graph Convolutional Network for Dynamic Graphs

IEEE Transactions on Knowledge and Data Engineering ◽

10.1109/tkde.2020.3033829 ◽

2020 ◽

pp. 1-1

Author(s):

Jingxin Liu ◽

Chang Xu ◽

Chang Yin ◽

Weiqiang Wu ◽

You Song

Keyword(s):

Dynamic Graphs ◽

Convolutional Network ◽

Temporal Graph

Download Full-text

Structure-Aware Multi-scale Hierarchical Graph Convolutional Network for Skeleton Action Recognition

10.1007/978-3-030-86365-4_24 ◽

2021 ◽

pp. 293-304

Author(s):

Changxiang He ◽

Shuting Liu ◽

Ying Zhao ◽

Xiaofei Qin ◽

Jiayuan Zeng ◽

...

Keyword(s):

Action Recognition ◽

Convolutional Network ◽

Multi Scale ◽

Hierarchical Graph

Download Full-text

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

Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence ◽

10.24963/ijcai.2019/614 ◽

2019 ◽

Cited By ~ 10

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.

Download Full-text

Predicting compound-protein interaction using hierarchical graph convolutional networks

10.1101/2021.10.04.463093 ◽

2021 ◽

Author(s):

Danh Bui-Thi ◽

Emmanuel Rivière ◽

Pieter Meysman ◽

Kris Laukens

Keyword(s):

Neural Networks ◽

Drug Discovery ◽

Small Molecules ◽

Convolutional Neural Networks ◽

Protein Interactions ◽

Computational Method ◽

Convolutional Network ◽

Convolutional Networks ◽

Generic Models ◽

Hierarchical Graph

AbstractMotivationConvolutional neural networks have enabled unprecedented breakthroughs in a variety of computer vision tasks. They have also drawn much attention from other domains, including drug discovery and drug development. In this study, we develop a computational method based on convolutional neural networks to tackle a fundamental question in drug discovery and development, i.e. the prediction of compound-protein interactions based on compound structure and protein sequence. We propose a hierarchical graph convolutional network (HGCN) to encode small molecules. The HGCN aggregates a molecule embedding from substructure embeddings, which are synthesized from atom embeddings. As small molecules usually share substructures, computing a molecule embedding from those common substructures allows us to learn better generic models. We then combined the HGCN with a one-dimensional convolutional network to construct a complete model for predicting compound-protein interactions. Furthermore we apply an explanation technique, Grad-CAM, to visualize the contribution of each amino acid into the prediction.ResultsExperiments using different datasets show the improvement of our model compared to other GCN-based methods and a sequence based method, DeepDTA, in predicting compound-protein interactions. Each prediction made by the model is also explainable and can be used to identify critical residues mediating the interaction.Availability and implementationhttps://github.com/banhdzui/cpi_hgcn.git

Download Full-text