Machine Learning
When Is ''Nearest Neighbor'' Meaningful?
ICDT '99 Proceedings of the 7th International Conference on Database Theory
On the Surprising Behavior of Distance Metrics in High Dimensional Spaces
ICDT '01 Proceedings of the 8th International Conference on Database Theory
Evaluation of key frame-based retrieval techniques for video
Computer Vision and Image Understanding - Special isssue on video retrieval and summarization
The CLEF 2004 cross-language image retrieval track
CLEF'04 Proceedings of the 5th conference on Cross-Language Evaluation Forum: multilingual Information Access for Text, Speech and Images
The Concentration of Fractional Distances
IEEE Transactions on Knowledge and Data Engineering
Unified framework for fast exact and approximate search in dissimilarity spaces
ACM Transactions on Database Systems (TODS)
Exploring multimedia in a keyword space
MM '08 Proceedings of the 16th ACM international conference on Multimedia
Comparing dissimilarity measures for content-based image retrieval
AIRS'08 Proceedings of the 4th Asia information retrieval conference on Information retrieval technology
The effect of distance metrics on boosting with dynamic weighting schemes
FSKD'09 Proceedings of the 6th international conference on Fuzzy systems and knowledge discovery - Volume 1
On nonmetric similarity search problems in complex domains
ACM Computing Surveys (CSUR)
Trading precision for speed: localised similarity functions
CIVR'05 Proceedings of the 4th international conference on Image and Video Retrieval
On fast non-metric similarity search by metric access methods
EDBT'06 Proceedings of the 10th international conference on Advances in Database Technology
Algorithmic exploration of axiom spaces for efficient similarity search at large scale
SISAP'12 Proceedings of the 5th international conference on Similarity Search and Applications
| Hi-index | 0.00 |
We have applied the concept of fractional distance measures, proposed by Aggarwal et al. [1], to content-based image retrieval. Our experiments show that retrieval performances of these measures consistently outperform the more usual Manhattan and Euclidean distance metrics when used with a wide range of high-dimensional visual features. We used the parameters learnt from a Corel dataset on a variety of different collections, including the TRECVID 2003 and ImageCLEF 2004 datasets. We found that the specific optimum parameters varied but the general performance increase was consistent across all 3 collections. To squeeze the last bit of performance out of a system it would be necessary to train a distance measure for a specific collection. However, a fractional distance measure with parameter p = 0.5 will consistently outperform both L1 and L2 norms.