Advances in Visual Concept Detection: Ten Years of TRECVID

Ville Viitaniemi, Mats Sjöberg, Markus Koskela, Satoru Ishikawa, Jorma Laaksonen

Research output: Chapter in Book/Report/Conference proceedingChapterScientificpeer-review

Abstract

In this chapter, we describe the structure and operation of the visual concept-detection subsystem of the PicSOM multimedia retrieval system. We evaluate several alternative techniques used for implementing this component and show the essential results of a series of experiments in the large-scale setups of the TRECVID video retrieval evaluation campaigns in 2005, 2009, and 2014. During these years, the PicSOM system has gone through substantial evolution in both the statistical features and the detection algorithms employed. Transition from global image features to the bag-of-visual-words features and recently further to convolutional deep neural network-based features is also justified in the light of our results. Overall, during the 10 years of participation in TRECVID, the PicSOM system has shown close to the state-of-the-art performance in this very rapidly developing field of research.
Original languageEnglish
Title of host publicationAdvances in Independent Component Analysis and Learning Machines
EditorsElla Bingham, Samuel Kaski, Jorma Laaksonen, Jouko Lampinen
Place of PublicationAmsterdam, The Netherlands
PublisherACADEMIC PRESS
Pages249-278
Edition1st Edition
ISBN (Electronic)9780128028070
ISBN (Print)9780128028063
DOIs
Publication statusPublished - 2015
MoE publication typeA3 Part of a book or another research book

Fingerprint Dive into the research topics of 'Advances in Visual Concept Detection: Ten Years of TRECVID'. Together they form a unique fingerprint.

Cite this