DocumentCode :
661283
Title :
Can ambiguous words be helpful in image-understanding systems?
Author :
Huiling Zhou ; Jiwei Hu ; Kin Man Lam
Author_Institution :
Dept. of Electron. & Inf. Eng., Hong Kong Polytech. Univ., Hong Kong, China
fYear :
2013
fDate :
Oct. 29 2013-Nov. 1 2013
Firstpage :
1
Lastpage :
4
Abstract :
A semantic gap always decreases the performance of the mapping for image-to-word, which is an important task in image understanding. Even efficient learning algorithms cannot solve this problem because: (1) of a lack of coincidence between the low-level features extracted from the visual data and the high-level information translated by human, and (2) an ambiguous word may lead to a wrong interpretation between low-level and high-level information. This paper introduces a discriminative model with a ranking function that optimizes the cost between the target word and the corresponding images, while simultaneously discovering the disambiguated senses of those words that are optimal for supervised tasks. Experiments were conducted using two datasets, and results show quite a promising result when compared with existing methods.
Keywords :
feature extraction; image classification; learning (artificial intelligence); K-nearest-neighbor-based models; cost optimization; discriminative classifier; discriminative model; high-level information; image-to-word mapping; image-understanding systems; learning algorithms; low-level feature extraction; low-level information; ranking function; semantic gap; visual data; Computational modeling; Feature extraction; Image color analysis; Image retrieval; Training; Vectors; Visualization;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Signal and Information Processing Association Annual Summit and Conference (APSIPA), 2013 Asia-Pacific
Conference_Location :
Kaohsiung
Type :
conf
DOI :
10.1109/APSIPA.2013.6694144
Filename :
6694144
Link To Document :
بازگشت