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

Ke Wang, Enrique Dunn, Mikel Rodriguez, Jan Michael Frahm

Research output: Contribution to journalArticlepeer-review

1 Scopus citations

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.

Original languageEnglish
Article number23
JournalIPSJ Transactions on Computer Vision and Applications
Volume9
Issue number1
DOIs
StatePublished - 1 Dec 2017

Keywords

  • 3D reconstruction
  • Video collection
  • Video representation
  • Video retrieval

Fingerprint

Dive into the research topics of 'Efficient video collection association using geometry-aware Bag-of-Iconics representations'. Together they form a unique fingerprint.

Cite this