Efficient video collection association using geometry-aware Bag-of-Iconics representations Public Deposited

Downloadable Content

Download PDF
  • Wang, Ke
    • Affiliation: College of Arts and Sciences, Department of Computer Science
  • Dunn, Enrique
    • Other Affiliation: Department of Computer Science, Stevens Institute of Technology, 1 Castle Point Terrace, Hoboken 07030, USA
  • Rodriguez, Mikel
    • Other Affiliation: MITRE Corporation, 202 Burlington Rd, Bedford 01730, USA
  • Frahm, Jan-Michael
    • Affiliation: College of Arts and Sciences, Department of Computer Science
  • Abstract Recent years have witnessed the dramatic evolution in visual data volume and processing capabilities. For example, technical advances have enabled 3D modeling from large-scale crowdsourced photo collections. Compared to static image datasets, exploration and exploitation of Internet video collections are still largely unsolved. To address this challenge, we first propose to represent video contents using a histogram representation of iconic imagery attained from relevant visual datasets. We then develop a data-driven framework for a fully unsupervised extraction of such representations. Our novel Bag-of-Iconics (BoI) representation efficiently analyzes individual videos within a large-scale video collection. We demonstrate our proposed BoI representation with two novel applications: (1) finding video sequences connecting adjacent landmarks and aligning reconstructed 3D models and (2) retrieving geometrically relevant clips from video collections. Results on crowdsourced datasets illustrate the efficiency and effectiveness of our proposed Bag-of-Iconics representation.
Date of publication
  • doi:10.1186/s41074-017-0034-3
Resource type
  • Article
Rights statement
  • In Copyright
Rights holder
  • The Author(s)
  • English
Bibliographic citation
  • IPSJ Transactions on Computer Vision and Applications. 2017 Dec 15;9(1):23
  • Springer Berlin Heidelberg

This work has no parents.