Please use this identifier to cite or link to this item: https://doi.org/10.1109/ICTAI.2012.44
Title: Automatic image annotation using word embedding learning
Authors: Chen, Q.
Yip, A.M. 
Tan, C.L. 
Keywords: embedding learning
image annotation
nearest neighbor
Issue Date: 2012
Citation: Chen, Q., Yip, A.M., Tan, C.L. (2012). Automatic image annotation using word embedding learning. Proceedings - International Conference on Tools with Artificial Intelligence, ICTAI 1 : 269-276. ScholarBank@NUS Repository. https://doi.org/10.1109/ICTAI.2012.44
Abstract: Automatically annotating words for images is a key to semantic-level image retrieval. Recently, several embedding learning based methods achieve good performance in this task which inspires this paper. Here we propose a novel word embedding model in which both images and words can be represented in the same embedding space. The embedding space is learnt in a discriminative nearest neighbor manner such that the annotation information could be propagated among neighbors. In order to accelerate model learning and testing, approximate-nearest-neighbor search is performed, and word embedding space is learnt in a stochastic manner. The experimental results demonstrate the effectiveness of the proposed method. © 2012 IEEE.
Source Title: Proceedings - International Conference on Tools with Artificial Intelligence, ICTAI
URI: http://scholarbank.nus.edu.sg/handle/10635/113929
ISBN: 9780769549156
ISSN: 10823409
DOI: 10.1109/ICTAI.2012.44
Appears in Collections:Staff Publications

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

Page view(s)

54
checked on Oct 19, 2018

Google ScholarTM

Check

Altmetric


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