Planned intervention: On Wednesday April 3rd 05:30 UTC Zenodo will be unavailable for up to 2-10 minutes to perform a storage cluster upgrade.
Published September 18, 2019 | Version v1
Book chapter Open

Finding Near-Duplicate Videos in Large-Scale Collections

  • 1. CERTH-ITI, Thessaloniki, Greece / Queen Mary University of London, UK
  • 2. CERTH-ITI, Thessaloniki, Greece
  • 3. Queen Mary University of London, UK

Description

This chapter discusses the problem of Near-Duplicate Video Retrieval (NDVR). The main objective of a typical NDVR approach is: given a query video, retrieve all near-duplicate videos in a video repository and rank them based on their similarity to the query. Several approaches have been introduced in the literature, which can be roughly classified in three categories based on the level of video matching, i.e., (i) video-level, (ii) frame-level, and (iii) filter-and-refine matching. Two methods based on video-level matching are presented in this chapter. The first is an unsupervised scheme that relies on a modified Bag-of-Words (BoW) video representation. The second is a s upervised method based on Deep Metric Learning (DML). For the development of both methods, features are extracted from the intermediate layers of Convolutional Neural Networks and leveraged as frame descriptors, since they offer a compact and informative image representation, and lead to increased system efficiency. Extensive evaluation has been conducted on publicly available benchmark datasets, and the presented methods are compared with state-of-the-art approaches, achieving the best results in all evaluation setups.

Files

InVID_book_ch4_NDVR.pdf

Files (3.2 MB)

Name Size Download all
md5:1d59edd724b1de2740d632e0abda74fd
3.2 MB Preview Download

Additional details

Funding

InVID – In Video Veritas – Verification of Social Media Video Content for the News Industry 687786
European Commission