Zobrazeno 1 - 10
of 189
pro vyhledávání: '"Minnan Luo"'
Publikováno v:
IEEE Transactions on Pattern Analysis and Machine Intelligence. 45:722-737
The rich content in various real-world networks such as social networks, biological networks, and communication networks provides unprecedented opportunities for unsupervised machine learning on graphs. This paper investigates the fundamental problem
Publikováno v:
Information Sciences. 607:1195-1210
Publikováno v:
PLoS ONE, Vol 14, Iss 4, p e0214809 (2019)
The cloud-based media streaming service is a promising paradigm for multimedia applications. It is attractive to media streaming service providers, who wish to deploy their media server clusters in a media cloud at reduced cost. Since the real-time l
Externí odkaz:
https://doaj.org/article/704807fa25834ba7928692069ea5881d
Publikováno v:
ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).
Publikováno v:
IEEE Transactions on Knowledge and Data Engineering. 34:764-775
Community detection is one of the fundamental tasks in graph mining, which aims to identify groups of nodes in complex networks. Recently, network embedding techniques have demonstrated their strong power in advancing the community detection task and
Publikováno v:
Data Science and Engineering. 7:16-29
Entity alignment (EA) aims to discover the equivalent entities in different knowledge graphs (KGs). It is a pivotal step for integrating KGs to increase knowledge coverage and quality. Recent years have witnessed a rapid increase of EA frameworks. Ho
Publikováno v:
IEEE Transactions on Pattern Analysis and Machine Intelligence. :1-14
An integral part of video analysis and surveillance is temporal activity detection, which means to simultaneously recognize and localize activities in long untrimmed videos. Currently, the most effective methods of temporal activity detection are bas
Few-shot learning (FSL) that aims to recognize novel classes with few labeled samples is troubled by its data scarcity. Though recent works tackle FSL with data augmentation-based methods, these models fail to maintain the discrimination and diversit
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::9c4af82b1462cb5ad4673e3649bbf2a5
https://hdl.handle.net/10453/168967
https://hdl.handle.net/10453/168967
Publikováno v:
Pattern Recognition. 139:109448
Current Graph Neural Networks (GNNs) suffer from the over-smoothing problem, which results in indistinguishable node representations and low model performance with more GNN layers. Many methods have been put forward to tackle this problem in recent y
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::eff62ba7b4002f847fb1dcf840113e1a
http://arxiv.org/abs/2208.09027
http://arxiv.org/abs/2208.09027