Naive (Bayes) at Forty: The Independence Assumption in Information Retrieval
ECML '98 Proceedings of the 10th European Conference on Machine Learning
Multiple View Geometry in Computer Vision
Multiple View Geometry in Computer Vision
Distribution of content words and phrases in text and language modelling
Natural Language Engineering
Distinctive Image Features from Scale-Invariant Keypoints
International Journal of Computer Vision
Modeling word burstiness using the Dirichlet distribution
ICML '05 Proceedings of the 22nd international conference on Machine learning
Trademark matching and retrieval in sports video databases
Proceedings of the international workshop on Workshop on multimedia information retrieval
Logo retrieval with a contrario visual query expansion
MM '09 Proceedings of the 17th ACM international conference on Multimedia
Interactive visual object search through mutual information maximization
Proceedings of the international conference on Multimedia
Descriptor learning for efficient retrieval
ECCV'10 Proceedings of the 11th European conference on computer vision conference on Computer vision: Part III
Scalable logo recognition in real-world images
Proceedings of the 1st ACM International Conference on Multimedia Retrieval
Image categorization using Fisher kernels of non-iid image models
CVPR '12 Proceedings of the 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Bundle min-hashing for logo recognition
Proceedings of the 3rd ACM conference on International conference on multimedia retrieval
| Hi-index | 0.00 |
Detecting logos in photos is challenging. A reason is that logos locally resemble patterns frequently seen in random images. We propose to learn a statistical model for the distribution of incorrect detections output by an image matching algorithm. It results in a novel scoring criterion in which the weight of correlated keypoint matches is reduced, penalizing irrelevant logo detections. In experiments on two very different logo retrieval benchmarks, our approach largely improves over the standard matching criterion as well as other state-of-the-art approaches.