Projection Bank: From High-Dimensional Data to Medium-Length Binary Codes

Li Liu, Mengyang Yu, Ling Shao

Research output: Chapter in Book/Report/Conference proceedingConference contribution

23 Citations (Scopus)
5 Downloads (Pure)


Recently, very high-dimensional feature representations, e.g., Fisher Vector, have achieved excellent performance for visual recognition and retrieval. However, these lengthy representations always cause extremely heavy computational and storage costs and even become unfeasible in some large-scale applications. A few existing techniques can transfer very high-dimensional data into binary codes, but they still require the reduced code length to be relatively long to maintain acceptable accuracies. To target a better balance between computational efficiency and accuracies, in this paper, we propose a novel embedding method called Binary Projection Bank (BPB), which can effectively reduce the very high-dimensional representations to medium-dimensional binary codes without sacrificing accuracies. Instead of using conventional single linear or bilinear projections, the proposed method learns a bank of small projections via the max-margin constraint to optimally preserve the intrinsic data similarity. We have systematically evaluated the proposed method on three datasets: Flickr 1M, ILSVR2010 and UCF101, showing competitive retrieval and recognition accuracies compared with state-of-the-art approaches, but with a significantly smaller memory footprint and lower coding complexity.
Original languageEnglish
Title of host publication2015 IEEE International Conference on Computer Vision (ICCV)
PublisherThe Institute of Electrical and Electronics Engineers (IEEE)
Publication statusPublished - 18 Feb 2016
Event2015 IEEE International Conference on Computer Vision (ICCV) - Santiago, Chile
Duration: 7 Dec 201513 Dec 2015


Conference2015 IEEE International Conference on Computer Vision (ICCV)

Cite this