Approximate nearest neighbors: towards removing the curse of dimensionality
STOC '98 Proceedings of the thirtieth annual ACM symposium on Theory of computing
Feature Extraction and a Database Strategy for Video Fingerprinting
VISUAL '02 Proceedings of the 5th International Conference on Recent Advances in Visual Information Systems
Computer Vision for Music Identification: Video Demonstration
CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 2 - Volume 02
Video linkage: group based copied video detection
CIVR '08 Proceedings of the 2008 international conference on Content-based image and video retrieval
Waveprint: Efficient wavelet-based audio fingerprinting
Pattern Recognition
A brief introduction to boosting
IJCAI'99 Proceedings of the 16th international joint conference on Artificial intelligence - Volume 2
| Hi-index | 0.00 |
In this paper, we present a novel approach for video fingerprinting by using boosted Harr-like features and direct hashing. Through employing a pairwise boosting method on a large set of features, our system can learn the top-M discriminative filters that are enable to efficient extracting video fingerprints. During query phase, we retrieve video clips by using a fast and accurate direct hashing, which minimizes perceptual Hamming distance between queries and a large database of pre-computed fingerprints. To demonstrate the superiority of our method, we also implement four other fingerprinting methods for comparisons. The experimental results indicate that our proposed method can significantly outperform those four methods in video retrieval.