Semi-automatic Flickr Group Suggestion

Abstract

Flickr groups are self-organized communities to share photos and conversations with common interest and have gained massive popularity. Users in Flickr have to manually assign each image to the appropriated group. Manual assignment requires users to be familiar with existing images in each group and it is intractable and tedious. Therefore it prohibits users from exploiting the relevant groups. For solution to the problem, group suggestion has attracted increasing attention recently, which aims to suggest groups to user for a specific image. Existing works pose group suggestion as the automatic group prediction problem with a purpose of predicting the groups of each image automatically. Despite of dramatic progress in automatic group prediction, the prediction results are still not accurate enough. In this paper, we propose a semiautomatic group suggestion approach with Human-in-the-Loop. Given a user's image collection, we employ the pre-built group classifiers to predict the group of each image. These predictions are used as the initial group suggestions. We then select a small number of representative images from user's collection and ask user to assign the groups of them. Once obtaining user's feedbacks on the representative images, we infer the groups of remaining images through group propagation over multiple sparse graphs among the images. We conduct experiment on 15 Flickr groups with 127,500 images. The experimental results demonstrate the proposed framework is able to provide accurate group suggestions with quite a small amount of user effort.