Graph convolutional neural network for human action recognition: A comprehensive survey

T Ahmad, L **, X Zhang, S Lai… - IEEE Transactions on …, 2021 - ieeexplore.ieee.org
Video-based human action recognition is one of the most important and challenging areas
of research in the field of computer vision. Human action recognition has found many …

[HTML][HTML] A survey on heterogeneous information network based recommender systems: Concepts, methods, applications and resources

J Liu, C Shi, C Yang, Z Lu, SY Philip - AI Open, 2022 - Elsevier
As an important way to alleviate information overload, a recommender system aims to filter
out irrelevant information for users and provides them items that they may be interested in. In …

A survey on knowledge graph-based recommender systems

Q Guo, F Zhuang, C Qin, H Zhu, X **e… - … on Knowledge and …, 2020 - ieeexplore.ieee.org
To solve the information explosion problem and enhance user experience in various online
applications, recommender systems have been developed to model users' preferences …

Meta-learning on heterogeneous information networks for cold-start recommendation

Y Lu, Y Fang, C Shi - Proceedings of the 26th ACM SIGKDD international …, 2020 - dl.acm.org
Cold-start recommendation has been a challenging problem due to sparse user-item
interactions for new users or items. Existing efforts have alleviated the cold-start issue to …

Learning community embedding with community detection and node embedding on graphs

S Cavallari, VW Zheng, H Cai, KCC Chang… - Proceedings of the …, 2017 - dl.acm.org
In this paper, we study an important yet largely under-explored setting of graph embedding,
ie, embedding communities instead of each individual nodes. We find that community …

Meta-graph based recommendation fusion over heterogeneous information networks

H Zhao, Q Yao, J Li, Y Song, DL Lee - Proceedings of the 23rd ACM …, 2017 - dl.acm.org
Heterogeneous Information Network (HIN) is a natural and general representation of data in
modern large commercial recommender systems which involve heterogeneous types of …

Graph CNNs with motif and variable temporal block for skeleton-based action recognition

YH Wen, L Gao, H Fu, FL Zhang, S **a - … of the AAAI conference on artificial …, 2019 - aaai.org
Hierarchical structure and different semantic roles of joints in human skeleton convey
important information for action recognition. Conventional graph convolution methods for …

Learning to count isomorphisms with graph neural networks

X Yu, Z Liu, Y Fang, X Zhang - Proceedings of the AAAI Conference on …, 2023 - ojs.aaai.org
Subgraph isomorphism counting is an important problem on graphs, as many graph-based
tasks exploit recurring subgraph patterns. Classical methods usually boil down to a …

Hetespaceywalk: A heterogeneous spacey random walk for heterogeneous information network embedding

Y He, Y Song, J Li, C Ji, J Peng, H Peng - Proceedings of the 28th ACM …, 2019 - dl.acm.org
Heterogeneous information network (HIN) embedding has gained increasing interests
recently. However, the current way of random-walk based HIN embedding methods have …

Motif-GCNs with local and non-local temporal blocks for skeleton-based action recognition

YH Wen, L Gao, H Fu, FL Zhang… - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
Recent works have achieved remarkable performance for action recognition with human
skeletal data by utilizing graph convolutional models. Existing models mainly focus on …