Pinview: Implicit Feedback in Content-Based Image Retrieval

144

Views

1

Downloads

Auer, Peter, Hussain, Zakria, Kaski, Samuel, Klami, Arto, Kujala, Jussi, Laaksonen, Jorma, Leung, Alex P., Pasupa, Kitsuchart and Shawe-Taylor, John (2010) Pinview: Implicit Feedback in Content-Based Image Retrieval In: The International Conference on Machine Learning (ICML 2010) Workshop on Reinforcement Learning and Search in Very Large Spaces, 25 June 2010, Haifa, Israel.

Abstract

This paper describes Pinview, a contentbased image retrieval system that exploits implicit relevance feedback during a search session. The goal is to retrieve interesting images and the relevance feedback could be eye movements or clicks on the images. Pinview contains several novel methods that infer the intent of the user. From relevance feedback and visual features of images Pinview learns a similarity metric between images which depends on the current interests of the user. It then retrieves images with a specialized reinforcement learning algorithm that balances the tradeoff between exploring new images and exploiting the already inferred interests of the user. In practise, Pinview is integrated to the content-based image retrieval system PicSOM, so it is possible to apply it to realworld image databases. Preliminary experiments show that eye movements provide a rich input modality from which it is possible to learn the interests of the user.

Item Type:

Conference or Workshop Item (Paper)

Subjects:

Subjects > Computer Science > Artificial Intelligence

Subjects > Computer Science > Computer Vision and Pattern Recognition

Subjects > Computer Science > Human-Computer Interaction

Subjects > Computer Science > Information Retrieval

Subjects > Computer Science > Machine Learning

Deposited by:

Kitsuchart Pasupa

Date Deposited:

2021-10-22 09:49:18

Last Modified:

2021-10-22 09:49:40

Impact and Interest:

Statistics