Automatic region of interest detection in tagged images
ICME'09 Proceedings of the 2009 IEEE international conference on Multimedia and Expo
ECCV'10 Proceedings of the 11th European conference on Computer vision: Part I
Building Rome on a cloudless day
ECCV'10 Proceedings of the 11th European conference on Computer vision: Part IV
Scene-based image retrieval by transitive matching
Proceedings of the 1st ACM International Conference on Multimedia Retrieval
Geometric Latent Dirichlet Allocation on a Matching Graph for Large-scale Image Datasets
International Journal of Computer Vision
Modeling and Recognition of Landmark Image Collections Using Iconic Scene Graphs
International Journal of Computer Vision
Sorting unorganized photo sets for urban reconstruction
Graphical Models
Distributed KNN-graph approximation via hashing
Proceedings of the 2nd ACM International Conference on Multimedia Retrieval
Towards exhaustive pairwise matching in large image collections
ECCV'12 Proceedings of the 12th international conference on Computer Vision - Volume Part I
Panoramic image search by similarity and adjacency for similar landscape discovery
WISE'12 Proceedings of the 13th international conference on Web Information Systems Engineering
An evaluation of two automatic landmark building discovery algorithms for city reconstruction
ECCV'10 Proceedings of the 11th European conference on Trends and Topics in Computer Vision - Volume Part II
Ranking consistency for image matching and object retrieval
Pattern Recognition
Object-based visual query suggestion
Multimedia Tools and Applications
Anytime merging of appearance-based maps
Autonomous Robots
Hi-index | 0.00 |
Automatic organization of large, unordered image collections is an extremely challenging problem with many potential applications. Often, what is required is that images taken in the same place, of the same thing, or of the same person be conceptually grouped together. This work focuses on grouping images containing thesame object, despite significant changes in scale, viewpoint and partial occlusions, in very large (1M+) image collections automatically gathered from Flickr. The scale of the data and the extreme variation in imaging conditions makes the problem very challenging. We describe a scalable method that first computes a matching graph over all the images. Image groups can then be mined from this graph using standard clustering techniques. The novelty we bring is that both the matching graph and the clustering methods are able to use the spatial consistency between the images arising from the common object (if there is one). We demonstrate our methods on a publicly available dataset of 5K images of Oxford, a 37K image dataset containing images of the Statue of Liberty, and a much larger 1M image dataset of Rome. This is, to our knowledge, the largest dataset to which image-based data mining has been applied.