Rocchio-based relevance feedback in video event retrieval

G.L.J. Pingen, M.H.T. de Boer, Robin Aly

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademic

1 Citation (Scopus)
16 Downloads (Pure)

Abstract

This paper investigates methods for user and pseudo relevance feedback in video event retrieval. Existing feedback methods achieve strong performance but adjust the ranking based on few individual examples. We propose a relevance feedback algorithm (ARF) derived from the Rocchio method, which is a theoretically founded algorithm in textual retrieval. ARF updates the weights in the ranking function based on the centroids of the relevant and non-relevant examples. Additionally, relevance feedback algorithms are often only evaluated by a single feedback mode (user feedback or pseudo feedback). Hence, a minor contribution of this paper is to evaluate feedback algorithms using a larger number of feedback modes. Our experiments use TRECVID Multimedia Event Detection collections. We show that ARF performs significantly better in terms of Mean Average Precision, robustness, subjective user evaluation, and run time compared to the state-of-the-art.
Original languageEnglish
Title of host publicationMultimedia Modeling
EditorsLaurent Amsaleg, Gylfi Þór Guðmundsson, Cathal Gurrin, Björn Þór Jónsson, Shin’ichi Satoh
Place of PublicationLondon
PublisherSpringer
Pages318-330
Number of pages13
Volume10133
ISBN (Print)978-3-319-51814-5
DOIs
Publication statusPublished - Jan 2017

Publication series

NameLecture Notes in Computer Science
PublisherSpringer Verlag
Volume10133
ISSN (Print)0302-9743

Keywords

  • EWI-27663
  • IR-104401
  • ARF
  • Rocchio
  • Video search
  • Relevance feedback
  • Information Retrieval

Fingerprint Dive into the research topics of 'Rocchio-based relevance feedback in video event retrieval'. Together they form a unique fingerprint.

Cite this