Proceedings of the 13th Annual ACM International Conference on Multimedia 2005
DOI: 10.1145/1101149.1101249
|View full text |Cite
|
Sign up to set email alerts
|

Learning an image-word embedding for image auto-annotation on the nonlinear latent space

Abstract: Latent Semantic Analysis (LSA) has shown encouraging performance for the problem of unsupervised image automatic annotation. LSA conducts annotation by keywords propagation on a linear Latent Space, which accounts for the underlying semantic structure of word and image features. In this paper, we formulate a more general nonlinear model, called Nonlinear Latent Space model, to reveal the latent variables of word and visual features more precisely. Instead of the basic propagation strategy, we present a novel i… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

0
9
0

Year Published

2006
2006
2017
2017

Publication Types

Select...
4
3
1

Relationship

0
8

Authors

Journals

citations
Cited by 15 publications
(9 citation statements)
references
References 10 publications
0
9
0
Order By: Relevance
“…The Probabilistic Latent Semantic analysis (PLSA) is then used to model the resulting uniform vectored data. A variation of this approach, namely the www.ijacsa.thesai.org nonlinear latent semantic analysis was proposed in [61] to annotate images automatically. Another approach consists in formulating automatic image annotation as a classification task where unlabelled images are assigned to a set of predefined concepts such as landscape, city and sunset [62].…”
Section: A Automatic Image Annotationmentioning
confidence: 99%
“…The Probabilistic Latent Semantic analysis (PLSA) is then used to model the resulting uniform vectored data. A variation of this approach, namely the www.ijacsa.thesai.org nonlinear latent semantic analysis was proposed in [61] to annotate images automatically. Another approach consists in formulating automatic image annotation as a classification task where unlabelled images are assigned to a set of predefined concepts such as landscape, city and sunset [62].…”
Section: A Automatic Image Annotationmentioning
confidence: 99%
“…Some approaches [1,8,12,13,22,20] deal directly with the problem of annotation, providing labels to either each region or the whole image. Others [4,17] treat the problem of annotation in two independent stages, first categorizing the images and then associating labels to them using the top ranked categories.…”
Section: Related Workmentioning
confidence: 99%
“…Our experiments are performed on 54, 000 images from the commonly used [1,3,4,8,12,13,17,22,20,21,14,19] Corel Stock Photo CDs, and 1, 000 publicly annotated images obtained from Yahoo! Flickr.…”
Section: Introductionmentioning
confidence: 99%
“…In order to improve image auto-annotation, many annotation methods have been proposed integrating different domains in annotation process, such as: ontology, semantic web [1], data mining and image mining [2] [3], genetic algorithms [4], Bayesian networks [5], separators to vast margins SVM [6], probabilistic model [7], nonlinear latent space [8] and linear latent space (LSA, PLSA).…”
Section: Introductionmentioning
confidence: 99%