A Study into Annotation Ranking Metrics in Community Contributed Image Corpora

详细信息    查看全文

• 作者：Mark Hughes (17)
  Gareth J. F. Jones (18)
  Noel E. O鈥機onnor (17)
  
• 关键词：Image annotation ; Landmark recognition ; Tag relevance
• 刊名：Lecture Notes in Computer Science
• 出版年：2014
• 出版时间：2014
• 年：2014
• 卷：1
• 期：1
• 页码：147-162
• 全文大小：4,142 KB
• 参考文献：1. Kennedy, L., Naaman, M., Ahern, S., Nair, R., Rattenbury, T.: How flickr helps us make sense of the world: context and content in community-contributed media collections. In: MULTIMEDIA 鈥?7: Proceedings of the 15th international conference on Multimedia, pp. 631鈥?40 (2007)
  2. Kennedy, L., Naaman, M.: Generating diverse and representative image search results for landmarks. In: WWW 鈥?8: Proceeding of the 17th international conference on World Wide Web, pp. 297鈥?06 (2008)
  3. Ahern, S., Naaman, M., Nair, R., Yang, J.: World explorer: visualizing aggregate data from unstructured text in geo-referenced collections. In: Proceedings of the Seventh ACM/IEEE-CS Joint Conference on Digital Libraries, pp. 1鈥?0 (2007)
  4. Xirong, L., Snoek, C., Worring, M.: Annotating images by harnessing worldwide user-tagged photos. In: Proceedings of the 2009 IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 3717鈥?720 (2009)
  5. Mahapatra, A., Wan, X., Tian, Y., Srivastava, J.: Augmenting image processing with social tag mining for landmark recognition. In: Lee, K.-T., Tsai, W.-H., Liao, H.-Y.M., Chen, T., Hsieh, J.-W., Tseng, C.-C. (eds.) MMM 2011 Part I. LNCS, vol. 6523, pp. 273鈥?83. Springer, Heidelberg (2011) f="http://dx.doi.org/10.1007/978-3-642-17832-0_26" target="_blank" title="It opens in new window">CrossRef
  6. Sigurbornsson, B., Van Zwol, R.: Flickr tag recommendation based on collective knowledge. In: WWW 鈥?8: Proceeding of the 17th International Conference on World Wide Web, pp. 327鈥?36 (2008)
  7. Bay, H., Tuytelaars, T., Van Gool, L.: SURF: speeded up robust features. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006, Part I. LNCS, vol. 3951, pp. 404鈥?17. Springer, Heidelberg (2006) f="http://dx.doi.org/10.1007/11744023_32" target="_blank" title="It opens in new window">CrossRef
  8. Nister, D., Stewenius, H.: Scalable recognition with a vocabulary tree. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 2161鈥?168 (2006)
  9. Sivic, J., Zisserman, A.: DVideo Google: a text retrieval approach to object matching in videos. In: Ninth IEEE International Conference on Computer Vision 2003, Proceedings, pp. 1470鈥?477 (2003)
  10. Lowe, D.: Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vis. 60, 91鈥?10 (2004) f="http://dx.doi.org/10.1023/B:VISI.0000029664.99615.94" target="_blank" title="It opens in new window">CrossRef
  11. Girardin, F., Blat, J.: Place this photo on a map: a study of explicit disclosure of location information. In: UbiComp (2007)
  12. Hollenstein, L.: Capturing vernacular geography from georeferenced tags. Masters thesis, University of Zurich (2008)
  
• 作者单位：Mark Hughes (17)
  Gareth J. F. Jones (18)
  Noel E. O鈥機onnor (17)
  
  17. CLARITY: Centre for Sensor Web Technologies, Dublin City University, Dublin 9, Ireland
  18. Centre for Next Generation Localisation, Dublin City University, Dublin 9, Ireland
  
• ISSN：1611-3349

文摘

Community contributed datasets are becoming increasing common in automated image annotation systems. One important issue with community image data is that there is no guarantee that the associated metadata is relevant. A method is required that can accurately rank the semantic relevance of community annotations. This should enable the extracting of relevant subsets from potentially noisy collections of these annotations. Having relevant, non-heterogeneous tags assigned to images should improve community image retrieval systems, such as Flickr, which are based on text retrieval methods. In the literature, the current state of the art approach to ranking the semantic relevance of Flickr tags is based on the widely used tf-idf metric. In the case of datasets containing landmark images, however, this metric is inefficient and can be improved upon. In this paper, we present a landmark recognition framework, that provides end-to-end automated recognition and annotation. In our study into automated annotation, we evaluate 5 alternate approaches to tf-idf to rank tag relevance in community contributed landmark image corpora. We carry out a thorough evaluation of each of these ranking metrics and results of this evaluation demonstrate that four of these proposed techniques outperform the current commonly-used tf-idf approach for this task. Our best performing evaluated approach achieves a significant F-Measure increase of .19 over tf-idf.