Ranking Without Learning: Towards Historical Relevance-based Ranking of Social Images

ABSTRACT

Tag-based Social Image Retrieval (TagIR) aims to find relevant social images using keyword queries. State-of-the-art TagIR techniques typically rank query results based on relevance, temporal or popularity criteria. However, these criteria may not always be sufficient to match diverse search intents of users. In this paper, we present a novel ranking scheme that ranks query results (images) based on their historical relevance. Informally, an image is historically relevant if its visual content is relevant to the query and it depicts objects, scenes, or events that are related to human history. To this end, we propose a learning-agnostic technique that leverages Wikipedia to quantify historical relevance of images. We empirically demonstrate the effectiveness of our ranking scheme using Flickr dataset.

References

1. T-S. Chua, et al. NUS-WIDE: A Real-world Web Image Database from National University of Singapore. In ACM CIVR, 2009.
2. . Gao, M. Wang, et al. Visual-Textual Joint Relevance Learning for Tag-Based Social Image Search. In textitIEEE Trans. on Image Processing, 22(1), 2013.
3. . Jain, M. Varma. Learning to Re-rank: Query-dependent Image Re-ranking Using Click Data. In textitWWW, 2011.
4. . Li, et al. Learning Social Tag Relevance by Neighbor Voting. textitIEEE Trans. Multimedia, 11(7), 2009.
5. . Li, et al. Unsupervised Multi-feature Tag Relevance Learning for Social Image Retrieval. In textitCIVR, 2010.
6. Z. Liu, et al. DeepFashion: Powering Robust Clothes Recognition and Retrieval with Rich Annotations. In CVPR, 2016.
7. . Milne, I. A. Witten. An Effective, Low-cost Measure of Semantic Relatedness Obtained from Wikipedia Links. textitProc. AAAI Workshop on Wikipedia and Artificial Intelligence, 2008.
8. . Smith, et al. Evaluating Implicit Judgments from Image Search Clickthrough Data. textitJASIST, 63(12), 2012.
9. . Sun, S. S. Bhowmick, et al. Tag-based Social Image Retrieval: An Empirical Evaluation. textitJASIST, 62(12), 2011.
10. . van Leuken, et al. Visual Diversification of Image Search Results. textitWWW, 2009.
11. L. Wu, Y. Wang, and J. Shepherd. Efficient Image and Tag Co-ranking: A Bregman Divergence Optimization Method. In textitACM MM, 2013.
12. . Xiao, et al. Exploring Tag Relevance for Image Tag Re-ranking. In textitSIGIR, 2012.
13. . Zhu, et al. Image Tag Refinement Towards Low-rank, Content-tag Prior and Error Sparsity. In textitACM MM, 2010.

Index Terms

• Information systems

  • Information retrieval

    • Specialized information retrieval

      • Multimedia and multimodal retrieval

        • Image search