Retrieving landmark and non-landmark images from community photo collections
Proceedings of the international conference on Multimedia
ECCV'10 Proceedings of the 11th European conference on computer vision conference on Computer vision: Part III
VIRaL: Visual Image Retrieval and Localization
Multimedia Tools and Applications
ATLAS: a probabilistic algorithm for high dimensional similarity search
Proceedings of the 2011 ACM SIGMOD International Conference on Management of data
On shape and the computability of emotions
Proceedings of the 20th ACM international conference on Multimedia
Towards indexing representative images on the web
Proceedings of the 20th ACM international conference on Multimedia
Towards measuring the visualness of a concept
Proceedings of the 21st ACM international conference on Information and knowledge management
MatchMiner: efficient spanning structure mining in large image collections
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part II
Towards exhaustive pairwise matching in large image collections
ECCV'12 Proceedings of the 12th international conference on Computer Vision - Volume Part I
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
PCM'12 Proceedings of the 13th Pacific-Rim conference on Advances in Multimedia Information Processing
Searching visual instances with topology checking and context modeling
Proceedings of the 3rd ACM conference on International conference on multimedia retrieval
Near-duplicate video retrieval: Current research and future trends
ACM Computing Surveys (CSUR)
Sim-min-hash: an efficient matching technique for linking large image collections
Proceedings of the 21st ACM international conference on Multimedia
Spatially aware feature selection and weighting for object retrieval
Image and Vision Computing
Object-based visual query suggestion
Multimedia Tools and Applications
Hi-index | 0.14 |
We propose a randomized data mining method that finds clusters of spatially overlapping images. The core of the method relies on the min-Hash algorithm for fast detection of pairs of images with spatial overlap, the so-called cluster seeds. The seeds are then used as visual queries to obtain clusters which are formed as transitive closures of sets of partially overlapping images that include the seed. We show that the probability of finding a seed for an image cluster rapidly increases with the size of the cluster. The properties and performance of the algorithm are demonstrated on data sets with 10^4, 10^5, and 5 \times 10^6 images. The speed of the method depends on the size of the database and the number of clusters. The first stage of seed generation is close to linear for databases sizes up to approximately 2^{34} \approx 10^{10} images. On a single 2.4 GHz PC, the clustering process took only 24 minutes for a standard database of more than 100,000 images, i.e., only 0.014 seconds per image.