Dual Structure Constrained Multimodal Feature Coding for Social Event Detection in Flickr Data

UM > Faculty of Science and Technology > DEPARTMENT OF COMPUTER AND INFORMATION SCIENCE

Status	已發表Published
	Dual Structure Constrained Multimodal Feature Coding for Social Event Detection in Flickr Data
	Yang, Z. G.; Li, Q.; Lu, Z.; Ma, Y.; Gong, Z. G.; Liu, W.
	2017-05-01
Source Publication	ACM Transactions on Internet Technology
ISSN	978-1-4503-2409-0
Pages	19:1-19:20
Abstract	In this article, a three-stage social event detection framework is proposed to discover events from Flickr-like data. Firstly, multiple bipartite graphs are constructed for the heterogeneous feature modalities to achieve fused features. Next, considering the geometrical structures of dictionary and data, a dual structure con- strained multimodal feature coding model is designed to learn discriminative feature codes by incorporating corresponding regularization terms into the objective. Finally, clustering models utilizing density or label knowledge and data recovery residual models are devised to discover real-world events. The experiments conducted on MediaEval 2014 SED dataset demonstrate the effectiveness of the proposed event detection approaches.
Keyword	Social media data fusion feature coding event detection
Language	英語English
The Source to Article	PB_Publication
PUB ID	25683
Document Type	Journal article
Collection	DEPARTMENT OF COMPUTER AND INFORMATION SCIENCE
Recommended Citation GB/T 7714	Yang, Z. G.,Li, Q.,Lu, Z.,et al. Dual Structure Constrained Multimodal Feature Coding for Social Event Detection in Flickr Data[J]. ACM Transactions on Internet Technology, 2017, 19:1-19:20.
APA	Yang, Z. G.., Li, Q.., Lu, Z.., Ma, Y.., Gong, Z. G.., & Liu, W. (2017). Dual Structure Constrained Multimodal Feature Coding for Social Event Detection in Flickr Data. ACM Transactions on Internet Technology, 19:1-19:20.
MLA	Yang, Z. G.,et al."Dual Structure Constrained Multimodal Feature Coding for Social Event Detection in Flickr Data".ACM Transactions on Internet Technology (2017):19:1-19:20.

Files in This Item:
There are no files associated with this item.

If you have any objections to this item, please fill out the form below and the administrator will contact you as soon as possible.
Content:
Email：	*
Affiliation No.
Verification Code:	Refresh

Any comments and suggestions are welcomed.
Title:	*
Content:
Email：	*
Verification Code:	Refresh