Multiple Measurements and Joint Dimensionality Reduction for Large Scale Image Search with Short Vectors - Archive ouverte HAL Access content directly
Conference Papers Year :

Multiple Measurements and Joint Dimensionality Reduction for Large Scale Image Search with Short Vectors

(1) , (2) , (1)
1
2

Abstract

This paper addresses the construction of a short-vector (128D) image representation for large-scale image and particular object retrieval. In particular, the method of joint dimensionality reduction of multiple vocabularies is considered. We study a variety of vocabulary generation techniques: different k-means initializations, different descriptotr transformations, different measurement regions for descriptor extraction. Our extensive evaluation shows that different combinations of vocabularies, each partitioning the descriptor space in a different yet complementary manner, results in a significant performance improvement, which exceeds the state-of-the-art.
Not file

Dates and versions

hal-01842288 , version 1 (18-07-2018)

Identifiers

Cite

Filip Radenović, Hervé Jégou, Ondrej Chum. Multiple Measurements and Joint Dimensionality Reduction for Large Scale Image Search with Short Vectors. ICMR 2015 - International Conference on Multimedia Retrieval, Jun 2015, Shanghai, China. pp.1-4, ⟨10.1145/2671188.2749366⟩. ⟨hal-01842288⟩
37 View
0 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More