Content-based Video Copy Detection using Binary Object Fingerprints

Research output: Chapters, Conference Papers, Creative and Literary WorksRGC 32 - Refereed conference paper (with host publication)peer-review

5 Scopus Citations
View graph of relations

Author(s)

  • Wilson Y. F. Yuen
  • Hok-Kwan Cheung
  • Peter H. W. Wong
  • Hon-Tung Luk
  • Kin-Wai Lau

Related Research Unit(s)

Detail(s)

Original languageEnglish
Title of host publication2018 IEEE International Conference on Signal Processing, Communications and Computing (ICSPCC 2018) - Conference Proceedings
PublisherInstitute of Electrical and Electronics Engineers, Inc.
ISBN (electronic)978-1-5386-7946-3
Publication statusPublished - Sept 2018

Publication series

NameIEEE International Conference on Signal Processing, Communications and Computing, ICSPCC

Conference

Title8th IEEE International Conference on Signal Processing, Communications and Computing, ICSPCC 2018
PlaceChina
CityQingdao
Period14 - 16 September 2018

Abstract

Content-based video copy detection in large-scale databases is still an open issue. One of the main reasons is that geometrical attack can easily surpass the global features of the frame while local features are inefficient in terms of compact representation and computational complexity. In this paper, we propose to use binary object fingerprints to represent video frame for improving the robustness of the video copy detection system. It is because salient object can be robustly detected using advanced convolutional neural network (CNN) based object detector. We proposed to use the well-known RetinaNet for generating object regions from the input frame and then these regions are used to generate binary fingerprints for fast copy detection in the database. This approach can maintain compact representation of video frame and high searching speed by binary fingerprint searching scheme. Experimental results show that the proposed approach can achieve about 10% higher recall rate with only sacrificing 1% prediction rate on VCDB dataset.

Research Area(s)

  • CNN, Content-based Copy Detection, Object Detection, Video Fingerprint

Citation Format(s)

Content-based Video Copy Detection using Binary Object Fingerprints. / Liu, Mengyang; Po, Lai-Man; Zhou, Chang et al.
2018 IEEE International Conference on Signal Processing, Communications and Computing (ICSPCC 2018) - Conference Proceedings. Institute of Electrical and Electronics Engineers, Inc., 2018. 8567827 (IEEE International Conference on Signal Processing, Communications and Computing, ICSPCC).

Research output: Chapters, Conference Papers, Creative and Literary WorksRGC 32 - Refereed conference paper (with host publication)peer-review