Text Mining for Automatic Image Tagging

Description:

This paper introduces several extractive approaches for automatic image tagging, relying exclusively on information mined from texts. Through evaluations on two datasets, the authors show that their methods exceed competitive baselines by a large margin, and compare favorably with the state-of-the-art that uses both textual and image features.

Creator(s):
Creation Date: August 2010
Partner(s):
UNT College of Engineering
Collection(s):
UNT Scholarly Works
Usage:
Total Uses: 65
Past 30 days: 13
Yesterday: 1
Creator (Author):
Leong, Chee Wee

University of North Texas

Creator (Author):
Mihalcea, Rada, 1974-

University of North Texas

Creator (Author):
Hassan, Samer

University of North Texas

Date(s):
  • Creation: August 2010
Description:

This paper introduces several extractive approaches for automatic image tagging, relying exclusively on information mined from texts. Through evaluations on two datasets, the authors show that their methods exceed competitive baselines by a large margin, and compare favorably with the state-of-the-art that uses both textual and image features.

Degree:
Physical Description:

9 p.

Language(s):
Subject(s):
Keyword(s): automatic image tagging | image databases | natural language | lexicon | tags
Source: Twenty-third Annual International Conference on Computational Linguistics (COLING), 2010, Beijing, China
Contributor(s):
Partner:
UNT College of Engineering
Collection:
UNT Scholarly Works
Identifier:
  • ARK: ark:/67531/metadc31028
Resource Type: Paper
Format: Text
Rights:
Access: Public