Learning query-dependent prefilters for scalable image retrieval

By Lorenzo Torresani, Martin Szummer, Andrew William Fitzgibbon. 2009

39 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Information Retrieval & Search

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Information Retrieval & Search

Citations in the corpus

Aggregating Local Image Descriptors into Compact Codes (2012, methodology): “The efficiency problem was partially addressed by the min-Hash approach [13], [14] and the pre-filtering method of [15].”
Efficient Object Category Recognition Using Classemes (2010, background): “Useful candidate classifiers might be those which make a sparse linear combination of input features, so that test cost is a small fraction of d per image; or predicate-based classifiers so that test images with nonzero score can be retrieved rapidly using inverted files [18,24], achieving test comp”
Image retrieval with geometry-preserving visual phrases (2011, background): “Another problem with existing methods [18, 21, 25] is that, because the total number of phrases can increase exponentially to the number of words in a phrase, they must select a subset from the entire phrase set.”
SIFT Meets CNN: A Decade Survey of Instance Retrieval (2016, background): “Visual word cooccurrences in the entire image are estimated [107] and aggregated [108], while in [109], [110], [29] visual word clusters within local neighborhoods are discovered.”
Avoiding Confusing Features in Place Recognition (2010, methodology): “Finally, the task of confuser detection has some similarities with the task of feature selection in category-level recognition [25,26,27] and retrieval [28,29,30].”
Beyond Instance-Level Image Retrieval: Leveraging Captions to Learn a Global Visual Representation for Semantic Retrieval (2017, unknown): “Another group of methods have concentrated on retrieving semanticallyrelated images, where “semantically related” is understood as displaying the same object category [65, 8], or sharing a set of tags [23, 22].”
Aggregating local descriptors into a compact image representation (2010, background): “However, these techniques still require a signiﬁcant amount of memory per image, and are more relevant in the context of near-duplicate image detection, as their search accuracy is signiﬁcantly lower than BOF.”