Issue No. 03 - July-Sept. (2013 vol. 20)
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/MMUL.2013.14
Philippe-Henri Gosselin , University of Cergy-Pontoise, France
David Picard , University of Cergy-Pontoise, France
Romain Negrel , University of Cergy-Pontoise, France
The main issues for Web-scale image retrieval are achieving good accuracy while retaining low computational time and memory footprint. This article proposes a compact image signature by aggregating tensors of visual descriptors. Efficient aggregation is achieved by preprocessing the descriptors. Compactness is achieved by projection and quantization of the signatures. The authors compare the proposed method to other efficient signatures on a 1 million images dataset and show the soundness of the approach.
Multimedia communication, Information retrieval, Video communication, Computer vision, Search methods, Image processing, computer vision, near-duplicate search, multimedia, image/video retrieval, image processing
Philippe-Henri Gosselin, David Picard, Romain Negrel, "Web-Scale Image Retrieval Using Compact Tensor Aggregation of Visual Descriptors", IEEE MultiMedia, vol. 20, no. , pp. 24-33, July-Sept. 2013, doi:10.1109/MMUL.2013.14