Query-adaptive asymmetrical dissimilarities for visual object retrieval - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2013

Query-adaptive asymmetrical dissimilarities for visual object retrieval

Hervé Jégou
  • Function : Author
  • PersonId : 833473
Shin'Ichi Satoh
  • Function : Author
  • PersonId : 929827

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.
Fichier principal
Vignette du fichier
iccv13_zhu.pdf (1.27 Mo) Télécharger le fichier
Vignette du fichier
iccv13_asym.png (76.55 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Format : Figure, Image
Loading...

Dates and versions

hal-00872957 , version 1 (14-10-2013)

Identifiers

  • HAL Id : hal-00872957 , version 1

Cite

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⟩
344 View
833 Download

Share

Gmail Facebook X LinkedIn More