UM  > 科技學院  > 電腦及資訊科學系
A semantic tree method for image classification and video action recognition
Liu, Chongwen1,2; Shang, Zhaowei2; Lin, Bo2; Tang, Yuan Yan3
2018-03
Source PublicationINTERNATIONAL JOURNAL OF WAVELETS MULTIRESOLUTION AND INFORMATION PROCESSING
ISSN0219-6913
Volume16Issue:2
Other Abstract

The multi-task learning (MTL) methods consider learning a problem together with other related problems simultaneously. The major challenge of MTL is how to selectively screen the shared information. The information of each task must be related to the others, but when sharing information between two unrelated tasks it degenerates the performance of both tasks. To ensure the related problems are related to the main task is the most important point in MTL. In this paper, we will design a novel algorithm to calculate the degrees of relationship among tasks by using a semantical space of features in each task and then build semantical tree to achieve better learning performance. We propose an MTL method under this algorithm which achieves good experimental performance. Our experiments are taken on both image classification and video action recognition, compared with the state-of-the-art MTL methods. Our method proposes good performance in the four public datasets.

KeywordMulti-task Learning Semantic Relationship Image Classification Video Action Recognition
DOIhttps://doi.org/10.1142/S0219691318400088
URLView the original
Indexed BySCI
Language英语
WOS Research AreaComputer Science ; Mathematics
WOS SubjectComputer Science, Software Engineering ; Mathematics, Interdisciplinary Applications
WOS IDWOS:000428416300009
PublisherWORLD SCIENTIFIC PUBL CO PTE LTD, 5 TOH TUCK LINK, SINGAPORE 596224, SINGAPORE
The Source to ArticleWOS
Fulltext Access
Citation statistics
Document TypeJournal article
CollectionDEPARTMENT OF COMPUTER AND INFORMATION SCIENCE
Corresponding AuthorLiu, Chongwen; Shang, Zhaowei; Lin, Bo; Tang, Yuan Yan
Affiliation1.School of Accounting Chongqing University of Technology, No. 69 Hongguang Avenue, Banan District Chongqing 400054, P. R. China
2.College of Computer Science, Chongqing University 174 Shazhengjie, Shapingba, Chongqing 400044, P. R. China
3.Faculty of Science and Technology University of Macau, Avenida da Universidade Taipa, Macau, P. R. China
Corresponding Author AffilicationFaculty of Science and Technology
Recommended Citation
GB/T 7714
Liu, Chongwen,Shang, Zhaowei,Lin, Bo,et al. A semantic tree method for image classification and video action recognition[J]. INTERNATIONAL JOURNAL OF WAVELETS MULTIRESOLUTION AND INFORMATION PROCESSING,2018,16(2).
APA Liu, Chongwen,Shang, Zhaowei,Lin, Bo,&Tang, Yuan Yan.(2018).A semantic tree method for image classification and video action recognition.INTERNATIONAL JOURNAL OF WAVELETS MULTIRESOLUTION AND INFORMATION PROCESSING,16(2).
MLA Liu, Chongwen,et al."A semantic tree method for image classification and video action recognition".INTERNATIONAL JOURNAL OF WAVELETS MULTIRESOLUTION AND INFORMATION PROCESSING 16.2(2018).
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Liu, Chongwen]'s Articles
[Shang, Zhaowei]'s Articles
[Lin, Bo]'s Articles
Baidu academic
Similar articles in Baidu academic
[Liu, Chongwen]'s Articles
[Shang, Zhaowei]'s Articles
[Lin, Bo]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Liu, Chongwen]'s Articles
[Shang, Zhaowei]'s Articles
[Lin, Bo]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.