Visual Synonyms for Landmark Image Retrieva
Efstratios Gavves, Cees Snoek and Arnold Smeulders
Computer Vision and Image Understanding
In this paper, we address the incoherence problem of the visual words in bag-of-words vocabularies. Dif- ferent from existing work, which assigns words based on closeness in descriptor space, we focus on iden- tifying pairs of independent, distant words – the visual synonyms – that are likely to host image patches of similar visual reality. We focus on landmark images, where the image geometry guides the detection of synonym pairs. Image geometry is used to find those image features that lie in the nearly identical phys- ical location, yet are assigned to different words of the visual vocabulary. Defined in this way, we evaluate the validity of visual synonyms. We also examine the closeness of synonyms in the L2-normalized feature space. We show that visual synonyms may successfully be used for vocabulary reduction. Furthermore, we show that combining the reduced visual vocabularies with synonym augmentation, we perform on par with the state-of-the-art bag-of-words approach, while having a 98% smaller vocabulary.
|Project Keyword:||Project Keyword UNSPECIFIED|
|Deposited By:||Christof Monz|
|Deposited On:||16 March 2012|