We found a match
Your institution may have access to this item. Find your institution then sign in to continue.
- Title
Multimodal concept detection in broadcast media: KavTan.
- Authors
Soysal, Medeni; Berker Loğoğlu, K.; Tekin, Mashar; Esen, Ersin; Saracoğlu, Ahmet; Oskay Acar, Banu; Can Ozan, Ezgi; Ateş, Tuğrul; Sevimli, Hakan; Sevinç, Müge; Atıl, İlkay; Özkan, Savaş; Ali Arabacı, Mehmet; Tankız, Seda; Karadeniz, Talha; Önür, Duygu; Selçuk, Sezin; Alatan, A.; Çiloğlu, Tolga
- 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.
- Subjects
MULTIMEDIA systems; BROADCAST data systems; BROADCASTING archives; INFORMATION retrieval; KEYWORD indexing; MULTIMODAL user interfaces
- Publication
Multimedia Tools & Applications, 2014, Vol 72, Issue 3, p2787
- ISSN
1380-7501
- Publication type
Article
- DOI
10.1007/s11042-013-1564-z