J-STAGE Home  >  Publications - Top  > Bibliographic Information

ITE Transactions on Media Technology and Applications
Vol. 4 (2016) No. 3 p. 251-258

Language:

http://doi.org/10.3169/mta.4.251

Special Section on Image and Video Analysis, Search, and Benchmark

This paper provides an extensive study on the availability of image representations based on convolutional networks (ConvNets) for the task of visual instance retrieval. Besides the choice of convolutional layers, we present an efficient pipeline exploiting multi-scale schemes to extract local features, in particular, by taking geometric invariance into explicit account, i.e. positions, scales and spatial consistency. In our experiments using five standard image retrieval datasets, we demonstrate that generic ConvNet image representations can outperform other state-of-the-art methods if they are extracted appropriately.

Copyright © 2016 The Institute of Image Information and Television Engineers

Article Tools

Share this Article