Text Mining for Automatic Image Tagging

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

• Type: Journal
• Year: 2010
• Where: COLING
• Authors: Chee Wee Leong, Rada Mihalcea, Samer Hassan
• Keywords: Automatic Image, COLING 2010, Competitive Baselines, Computational Linguistics, Extractive Approaches