Abstract | ||
---|---|---|
We present a novel compact image descriptor for large scale image search. Our proposed descriptor - Geometric VLAD (gVLAD) is an extension of VLAD (Vector of Locally Aggregated Descriptors) that incorporates weak geometry information into the VLAD framework. The proposed geometry cues are derived as a membership function over keypoint angles which contain evident and informative information but yet often discarded. A principled technique for learning the membership function by clustering angles is also presented. Further, to address the overhead of iterative codebook training over real-time datasets, a novel codebook adaptation strategy is outlined. Finally, we demonstrate the efficacy of proposed gVLAD based retrieval framework where we achieve more than 15% improvement in mAP over existing benchmarks. |
Year | Venue | Field |
---|---|---|
2014 | arXiv: Computer Vision and Pattern Recognition | Data mining,Pattern recognition,Computer science,Artificial intelligence,Cluster analysis,Membership function,Machine learning,Codebook |
DocType | Volume | Citations |
Journal | abs/1403.3829 | 7 |
PageRank | References | Authors |
0.43 | 11 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Zixuan Wang | 1 | 20 | 5.18 |
Wei Di | 2 | 228 | 10.40 |
Anurag Bhardwaj | 3 | 298 | 16.76 |
Vignesh Jagadeesh | 4 | 217 | 12.74 |
Robinson Piramuthu | 5 | 289 | 18.00 |