Leveraging Implicit Spatial Information In Global Features For Image Retrieval - Archive ouverte HAL Access content directly
Conference Papers Year : 2018

Leveraging Implicit Spatial Information In Global Features For Image Retrieval

Abstract

Most image retrieval methods use global features that aggregate local distinctive patterns into a single representation. However, the aggregation process destroys the relative spatial information by considering orderless sets of local descriptors. We propose to integrate relative spatial information into the aggregation process by taking into account co-occurrences of local patterns in a tensor framework. The resulting signature called Improved Spatial Tensor Aggregation (ISTA) is able to reach state of the art performances on well known datasets such as Holidays, Oxford5k and Paris6k.
No file

Dates and versions

hal-01816918 , version 1 (15-06-2018)

Identifiers

  • HAL Id : hal-01816918 , version 1

Cite

Pierre Jacob, David Picard, Aymeric Histace, Edouard Klein. Leveraging Implicit Spatial Information In Global Features For Image Retrieval . IEEE International Conference in Image Processing, Oct 2018, Athens, Greece. ⟨hal-01816918⟩
88 View
0 Download

Share

Gmail Facebook X LinkedIn More