Paper Info
Title
Multi-Label Learning With Fused Multimodal Bi-Relational Graph
Abstract
The problem of multi-label image classification using multiple feature modalities is considered in this work. Given a collection of images with partial labels, we first model the association between different feature modalities and the images labels. These associations are then propagated with a graph diffusion kernel to classify the unlabeled images. Towards this objective, a novel Fused Multimodal Bi-relational Graph representation is proposed, with multiple graphs corresponding to different feature modalities, and one graph corresponding to the image labels. Such a representation allows for effective exploitation of both feature complementariness and label correlation. This contrasts with previous work where these two factors are considered in isolation. Furthermore, we provide a solution to learn the weight for each image graph by estimating the discriminative power of the corresponding feature modality. Experimental results with our proposed method on two standard multi-label image datasets are very promising.
Year
DOI
Venue
2014
10.1109/TMM.2013.2291218
IEEE Transactions on Multimedia
Keywords
Field
DocType
multimodal,standard multilabel image datasets,unlabeled images,learning (artificial intelligence),fused multimodal bi-relational graph representation,image classification,multi-label classification,multiple feature modalities,graph diffusion kernel,graph theory,graph-based semi-supervised learning,multilabel image classification,multilabel learning,learning artificial intelligence
Kernel (linear algebra),Graph kernel,Modalities,Graph theory,Computer vision,Pattern recognition,Computer science,Contrast (statistics),Artificial intelligence,Contextual image classification,Discriminative model,Graph (abstract data type)
Journal
Volume
Issue
ISSN
16
2
1520-9210
Citations 
PageRank 
References 
14
0.48
38
Authors
3
Name
Order
Citations
PageRank
Jiejun Xu114711.11
Vignesh Jagadeesh221712.74
B. S. Manjunath37561783.37