Object Recognition from Local Scale-Invariant Features
ICCV '99 Proceedings of the International Conference on Computer Vision-Volume 2 - Volume 2
Locality-sensitive hashing scheme based on p-stable distributions
SCG '04 Proceedings of the twentieth annual symposium on Computational geometry
A posteriori multi-probe locality sensitive hashing
MM '08 Proceedings of the 16th ACM international conference on Multimedia
Logo retrieval with a contrario visual query expansion
MM '09 Proceedings of the 17th ACM international conference on Multimedia
Unsupervised Object Discovery: A Comparison
International Journal of Computer Vision
Object Discovery by Clustering Correlated Visual Word Sets
ICPR '10 Proceedings of the 2010 20th International Conference on Pattern Recognition
Scalable triangulation-based logo recognition
Proceedings of the 1st ACM International Conference on Multimedia Retrieval
Consistent visual words mining with adaptive sampling
Proceedings of the 1st ACM International Conference on Multimedia Retrieval
CVPR '11 Proceedings of the 2011 IEEE Conference on Computer Vision and Pattern Recognition
Total recall II: Query expansion revisited
CVPR '11 Proceedings of the 2011 IEEE Conference on Computer Vision and Pattern Recognition
On the Annotation of Web Videos by Efficient Near-Duplicate Search
IEEE Transactions on Multimedia
Discovering favorite views of popular places with iconoid shift
ICCV '11 Proceedings of the 2011 International Conference on Computer Vision
Small objects query suggestion in a large web-image collection
Proceedings of the 21st ACM international conference on Multimedia
OTMedia: the French TransMedia news observatory
Proceedings of the 21st ACM international conference on Multimedia
Hi-index | 0.00 |
This paper presents a scalable method for automatically discovering frequent visual objects in large multimedia collections even if their size is very small. It first formally revisits the problem of mining or discovering such objects, and then generalizes two kinds of existing methods for probing candidate object seeds: weighted adaptive sampling and hashing-based methods. The idea is that the collision frequencies obtained with hashing-based methods can actually be converted into a prior probability density function given as input to a weighted adaptive sampling algorithm. This allows for an evaluation of any hashing scheme effectiveness in a more generalized way, and a comparison with other priors, e.g. guided by visual saliency concerns. We then introduce a new hashing strategy, working first at the visual level, and then at the geometric level. This strategy allows us to integrate weak geometric constraints into the hashing phase itself and not only neighborhood constraints as in previous works. Experiments conducted on a new dataset introduced in this paper will show that using this new hashing-based prior allows a drastic reduction of the number of tentative probes required to discover small objects instantiated several times in a large dataset.