Unconstrained Multimodal Multi-Label Learning | |
Huang, Yan1![]() ![]() ![]() | |
Source Publication | IEEE TRANSACTIONS ON MULTIMEDIA
![]() |
2015-11-01 | |
Volume | 17Issue:11Pages:1923-1935 |
Subtype | Article |
Abstract | Multimodal learning has been mostly studied by assuming that multiple label assignments are independent of each other and all the modalities are available. In this paper, we consider a more general problem where the labels contain dependency relationships and some modalities are likely to be missing. To this end, we propose a multi-label conditional restricted Boltzmann machine (ML-CRBM), which handles modality completion, fusion, and multi-label prediction in a unified framework. The proposed model is able to generate missing modalities based on observed ones, by explicitly modelling and sampling their conditional distributions. After that, it can discriminatively fuse multiple modalities to obtain shared representations under the supervision of class labels. To consider the co-occurrence of the labels, the proposed model formulates the multi-label prediction as a max-margin-based multi-task learning problem. Model parameters can be jointly learned by seeking a balance between being generative for modality generation and being discriminative for label prediction. We perform a series of experiments in terms of classification, visualization, and retrieval, and the experimental results clearly demonstrate the effectiveness of our method. |
Keyword | Multi-label Learning Multi-task Learning Multimodal Learning Restricted Boltzmann Machine |
WOS Headings | Science & Technology ; Technology |
DOI | 10.1109/TMM.2015.2476658 |
WOS Keyword | NEURAL-NETWORKS ; REPRESENTATION ; COLOR |
Indexed By | SCI |
Language | 英语 |
Funding Organization | National Natural Science Foundation of China(61175003 ; National Basic Research Program of China(2012CB316300) ; 61202328 ; 61572504 ; 61420106015) |
WOS Research Area | Computer Science ; Telecommunications |
WOS Subject | Computer Science, Information Systems ; Computer Science, Software Engineering ; Telecommunications |
WOS ID | WOS:000364102400006 |
Citation statistics | |
Document Type | 期刊论文 |
Identifier | http://ir.ia.ac.cn/handle/173211/10497 |
Collection | 智能感知与计算 |
Affiliation | 1.Chinese Acad Sci CASIA, Inst Automat, Natl Lab Pattern Recognit, Ctr Res Intelligent Percept & Comp, Beijing 100190, Peoples R China 2.CASIA, Inst Automat, CAS Ctr Excellence Brain Sci & Intelligence Techn, Beijing 100190, Peoples R China |
First Author Affilication | Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China |
Recommended Citation GB/T 7714 | Huang, Yan,Wang, Wei,Wang, Liang. Unconstrained Multimodal Multi-Label Learning[J]. IEEE TRANSACTIONS ON MULTIMEDIA,2015,17(11):1923-1935. |
APA | Huang, Yan,Wang, Wei,&Wang, Liang.(2015).Unconstrained Multimodal Multi-Label Learning.IEEE TRANSACTIONS ON MULTIMEDIA,17(11),1923-1935. |
MLA | Huang, Yan,et al."Unconstrained Multimodal Multi-Label Learning".IEEE TRANSACTIONS ON MULTIMEDIA 17.11(2015):1923-1935. |
Files in This Item: | Download All | |||||
File Name/Size | DocType | Version | Access | License | ||
UMMLL.pdf(3011KB) | 期刊论文 | 作者接受稿 | 开放获取 | CC BY-NC-SA | View Download |
Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.
Edit Comment