Location sensitive indexing for image-based advertising

ABSTRACT

This paper introduces the architecture of our location sensitive indexing model which is used in a platform designed to deliver advertisements to users who primarily utilize images as queries instead of textual keywords. The indexing model facilitates an advertiser's ability to bid on images, such as billboards or logos, in order to obtain user feedback in judging image attractiveness. Additionally, the model enables automatic evaluation of advertisement popularity by mining users' query logs, which is critical for generating advertisement recommendations. The location sensitive architecture of this model enables effective and efficient functionality in large-scale scenarios. In the model's structure, our Location Sensitive Visual Indexing model (LSVI) incorporates location information that subdivides geographical regions for precise and localized image matching. By collecting feedback from mobile users, location-based mining can also help discover popular advertisements as well as their representative images. We have deployed our platform into a real-world advertising system in Beijing, China, which demonstrates effective results in comparative studies with both alternative and state-of-the-art approaches.

REFERENCES

• 1: W. Jiang, D. Liu, X. Xie, M. R. Scott, J. Tien, D. Xiang: An Online Advertisement Platform Based On Image Content Bidding. ICME, 2009.
• 2: D. G. Lowe: Distinctive image features from scale-invariant key-points. IJCV, 20(2), 91--110, 2004
• 3: W. Chu, C. Lin: Automatic Selection of Representative Photo and Smart Thumbnailing Using Near-Duplicate Detection. ACM Multimedia 2008.
• 4: A, Guttman. R-TREES: A Dynamic Index Structure For Spatial Searching, ACM SIGMOD, 1984.
• 5: R. Lee, et al. Optimization of geographic area to a web page for two-dimensional range query processing. IEEE WISEW, 2003.
• 6: D. Nistér, H. Stewénius: Scalable Recognition with a vocabulary tree. CVPR, 2006.
• 7: Y. Theodoridis, E. Stefanakis, and T. Sellis, Efficient cost models for spatial queries using R-Trees. IEEE Transactions on Knowledge and Data Engineering, Volume 12, Issue 1, 2000, PP.19--32.
• 8: G. Schindler, M. Brown: City-scale location recognition. CVPR. 2007.
• 9: R. Ji, X. Xie, H. Yao, W. Ma: Vocabulary Hierarchy Optimization for Effective and Transferable Retrieval, CVPR, 2009.
• 10: R. Ji, X. Xie, H. Yao, W.-Y. Ma, Y. Wu: Vocabulary Tree Incremental Indexing for Scalable Scene Recognition, ICME, 2008.

INDEX TERMS

Primary Classification:
  I. Computing Methodologies
  I.5 PATTERN RECOGNITION
      I.5.4 Applications
          Subjects: Computer vision

Additional Classification:
  I. Computing Methodologies
  I.4 IMAGE PROCESSING AND COMPUTER VISION
      I.4.8 Scene Analysis
          Subjects: Object recognition

General Terms:
Algorithms, Design, Experimentation

Keywords:
hybrid indexing structure, image content bidding, image search