IMAGE RE-RANKING BASED ON TOPIC DIVERGENCE

Author (s) : J.Malathi, M.Sivabalan

---

Abstract :

Tag-based image retrieval is an important method to find images shared by users in social networks. However, it is challenging to make the top ranked results relevant and diverse. In this paper, we propose a topic diverse ranking approach for tag-based image retrieval with the consideration of promoting the topic coverage performance.Our approach first constructs a tag graph based on the similarity between each tag. Then, a community detection method is conducted to mine the topic community of each tag. After that, inter-community and intra-community ranking are introduced to obtain the final retrieved results.In the inter-community ranking process, an adaptive random walk model is employed to rank the community based on the multi-information of each topic community. Besides, we build an inverted index structure for images to accelerate the searching process. Experimental results on Flicker dataset and NUS-Wide datasets show the effectiveness of the proposed approach.

Keywords : Image retrieval, tag-based retrieval, topic diversity, community detection, random walk, inverted index

Conference Date : 13/11/2020

Pages : 185

Paper ID : 20185