Skip to Main content Skip to Navigation
New interface
Conference papers

Query-adaptive asymmetrical dissimilarities for visual object retrieval

Cai-Zhi Zhu 1 Hervé Jégou 2 Shin'Ichi Satoh 1 
2 TEXMEX - Multimedia content-based indexing
IRISA - Institut de Recherche en Informatique et Systèmes Aléatoires, Inria Rennes – Bretagne Atlantique
Abstract : Visual object retrieval aims at retrieving, from a collection of images, all those in which a given query object appears. It is inherently asymmetric: the query object is mostly included in the database image, while the converse is not necessarily true. However, existing approaches mostly compare the images with symmetrical measures, without considering the different roles of query and database. This paper first measure the extent of asymmetry on large-scale public datasets reflecting this task. Considering the standard bag-of-words representation, we then propose new asymmetrical dissimilarities accounting for the different inlier ratios associated with query and database images. These asymmetrical measures depend on the query, yet they are compatible with an inverted file structure, without noticeably impacting search efficiency. Our experiments show the benefit of our approach, and show that the visual object retrieval task is better treated asymmetrically, in the spirit of state-of-the-art text retrieval.
Document type :
Conference papers
Complete list of metadata

Cited literature [24 references]  Display  Hide  Download
Contributor : Hervé Jégou Connect in order to contact the contributor
Submitted on : Monday, October 14, 2013 - 5:25:04 PM
Last modification on : Tuesday, July 5, 2022 - 8:38:34 AM
Long-term archiving on: : Wednesday, January 15, 2014 - 9:10:16 AM


Files produced by the author(s)


  • HAL Id : hal-00872957, version 1


Cai-Zhi Zhu, Hervé Jégou, Shin'Ichi Satoh. Query-adaptive asymmetrical dissimilarities for visual object retrieval. ICCV - International Conference on Computer Vision, Dec 2013, Sydney, Australia. ⟨hal-00872957⟩



Record views


Files downloads