Learning to re-rank: query-dependent image re-ranking using click data

Our objective is to improve the performance of keyword based image search engines by re-ranking their baseline results. To this end, we address three limitations of existing search engines in this paper. First, there is no straightforward, fully automated way of going from textual queries to visual features. Image search engines are therefore forced to rely on static and textual features alone for ranking. Visual features are used only for secondary tasks such as finding similar images. Second, image rankers are trained on query-image pairs labeled with relevance judgments determined by human experts. Such labels are well known to be noisy due to various factors including ambiguous queries, unknown user intent and subjectivity in human judgments. This leads to learning a sub-optimal ranker. Finally, a static ranker is typically built to handle disparate user queries. The ranker is therefore unable to adapt its parameters to suit the query at hand which again leads to sub-optimal resu...

• Type: Journal
• Year: 2011
• Where: WWW
• Authors: Vidit Jain, Manik Varma
• Keywords: Image, Image Search Engine, Internet Technology, Search Engine, WWW 2011