Tampere University of Technology

TUTCRIS Research Portal

Multimodal concept detection in broadcast media: KavTan

Research output: Contribution to journalArticleScientificpeer-review

Details

Original languageEnglish
Pages (from-to)2787-2832
Number of pages46
JournalMultimedia Tools and Applications
Volume72
Issue number3
DOIs
Publication statusPublished - Oct 2014
Externally publishedYes
Publication typeA1 Journal article-refereed

Abstract

Concept detection stands as an important problem for efficient indexing and retrieval in large video archives. In this work, the KavTan System, which performs high-level semantic classification in one of the largest TV archives of Turkey, is presented. In this system, concept detection is performed using generalized visual and audio concept detection modules that are supported by video text detection, audio keyword spotting and specialized audio-visual semantic detection components. The performance of the presented framework was assessed objectively over a wide range of semantic concepts (5 high-level, 14 visual, 9 audio, 2 supplementary) by using a significant amount of precisely labeled ground truth data. KavTan System achieves successful high-level concept detection performance in unconstrained TV broadcast by efficiently utilizing multimodal information that is systematically extracted from both spatial and temporal extent of multimedia data.

Keywords

  • Intelligent multimedia systems, Concept detection, Broadcast video indexing, Multimodal semantic indexing, RELEVANCE FEEDBACK, IMAGE RETRIEVAL, AUDIO CLASSIFICATION, FEATURES, RECOGNITION, ALGORITHMS, VIDEO, NEWS

Publication forum classification

Field of science, Statistics Finland