Unsupervised Deep Video Hashing via Balanced Code for Large-Scale Video Retrieval

Gengshen Wu, Jungong Han, Yuchen Guo, Li Liu, Guiguang Ding, Qiang Ni, Ling Shao

Research output: Contribution to journalArticlepeer-review

118 Citations (SciVal)
29 Downloads (Pure)

Abstract

This paper proposes a deep hashing framework, namely Unsupervised Deep Video Hashing (UDVH), for largescale video similarity search with the aim to learn compact yet effective binary codes. Our UDVH produces the hash codes in a self-taught manner by jointly integrating discriminative video representation with optimal code learning, where an efficient alternating approach is adopted to optimize the objective function. The key differences from most existing video hashing methods lie in 1) UDVH is an unsupervised hashing method that generates hash codes by cooperatively utilizing feature clustering and a specifically-designed binarization with the original neighborhood structure preserved in the binary space; 2) a specific rotation is developed and applied onto video features such that the variance of each dimension can be balanced, thus facilitating the subsequent quantization step. Extensive experiments performed on three popular video datasets show that UDVH is overwhelmingly better than the state-of-the-arts in terms of various evaluation metrics, which makes it practical in real-world applications.

Original languageEnglish
Article number8540456
Pages (from-to)1993-2007
Number of pages15
JournalIEEE Transactions on Image Processing
Volume28
Issue number4
Early online date19 Nov 2018
DOIs
Publication statusPublished - 30 Apr 2019
Externally publishedYes

Keywords

  • Video hashing
  • balanced rotation
  • deep learning
  • feature representation
  • similarity retrieval

Fingerprint

Dive into the research topics of 'Unsupervised Deep Video Hashing via Balanced Code for Large-Scale Video Retrieval'. Together they form a unique fingerprint.

Cite this