Metric learning for large scale image classification: generalizing to new classes at near-zero cost
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part II
Negative evidences and co-occurences in image retrieval: the benefit of PCA and whitening
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part II
Data-driven vehicle identification by image matching
ECCV'12 Proceedings of the 12th international conference on Computer Vision - Volume 2
Efficient image signatures and similarities using tensor products of local descriptors
Computer Vision and Image Understanding
Retrieving geo-location of videos with a divide & conquer hierarchical multimodal approach
Proceedings of the 3rd ACM conference on International conference on multimedia retrieval
Signature matching distance for content-based image retrieval
Proceedings of the 3rd ACM conference on International conference on multimedia retrieval
Tag completion based on belief theory and neighbor voting
Proceedings of the 3rd ACM conference on International conference on multimedia retrieval
Online multimodal deep similarity learning with application to image retrieval
Proceedings of the 21st ACM international conference on Multimedia
Revisiting the VLAD image representation
Proceedings of the 21st ACM international conference on Multimedia
Activity detection and recognition of daily living events
Proceedings of the 1st ACM international workshop on Multimedia indexing and information retrieval for healthcare
Search-based relevance association with auxiliary contextual cues
Proceedings of the 21st ACM international conference on Multimedia
Spatially aware feature selection and weighting for object retrieval
Image and Vision Computing
Evaluating multimedia features and fusion for example-based event detection
Machine Vision and Applications
Image Classification with the Fisher Vector: Theory and Practice
International Journal of Computer Vision
Compact vectors of locally aggregated tensors for 3D shape retrieval
3DOR '13 Proceedings of the Sixth Eurographics Workshop on 3D Object Retrieval
| Hi-index | 0.14 |
This paper addresses the problem of large-scale image search. Three constraints have to be taken into account: search accuracy, efficiency, and memory usage. We first present and evaluate different ways of aggregating local image descriptors into a vector and show that the Fisher kernel achieves better performance than the reference bag-of-visual words approach for any given vector dimension. We then jointly optimize dimensionality reduction and indexing in order to obtain a precise vector comparison as well as a compact representation. The evaluation shows that the image representation can be reduced to a few dozen bytes while preserving high accuracy. Searching a 100 million image data set takes about 250 ms on one processor core.