Unsupervised learning by probabilistic latent semantic analysis
Machine Learning
On the Resemblance and Containment of Documents
SEQUENCES '97 Proceedings of the Compression and Complexity of Sequences 1997
Object Recognition from Local Scale-Invariant Features
ICCV '99 Proceedings of the International Conference on Computer Vision-Volume 2 - Volume 2
The Journal of Machine Learning Research
Asymmetric distance estimation with sketches for similarity search in high-dimensional spaces
Proceedings of the 31st annual international ACM SIGIR conference on Research and development in information retrieval
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
I-SEARCH: a multimodal search engine based on rich unified content description (RUCoD)
Proceedings of the 21st international conference companion on World Wide Web
Large vocabulary quantization for searching instances from videos
Proceedings of the 2nd ACM International Conference on Multimedia Retrieval
Scalable mining of small visual objects
Proceedings of the 20th ACM international conference on Multimedia
Object-based visual query suggestion
Multimedia Tools and Applications
Hi-index | 0.00 |
State-of-the-art large-scale object retrieval systems usually combine efficient Bag-of-Words indexing models with a spatial verification re-ranking stage to improve query performance. In this paper we propose to directly discover spatially verified visual words as a batch process. Contrary to previous related methods based on feature sets hashing or clustering, we suggest not trading recall for efficiency by sticking on an accurate two-stage matching strategy. The problem then rather becomes a sampling issue: how to effectively and efficiently select relevant query regions while minimizing the number of tentative probes? We therefore introduce an adaptive weighted sampling scheme, starting with some prior distribution and iteratively converging to unvisited regions. Interestingly, the proposed paradigm is generalizable to any input prior distribution, including specific visual concept detectors or efficient hashing-based methods. We show in the experiments that the proposed method allows to discover highly interpretable visual words while providing excellent recall and image representativity.