Details
| Originalsprache | Englisch |
|---|---|
| Titel des Sammelwerks | ICSC 2009 |
| Untertitel | 2009 IEEE International Conference on Semantic Computing |
| Seiten | 109-115 |
| Seitenumfang | 7 |
| Publikationsstatus | Veröffentlicht - 30 Okt. 2009 |
| Extern publiziert | Ja |
| Veranstaltung | ICSC 2009 - 2009 IEEE International Conference on Semantic Computing - Berkeley, CA, USA / Vereinigte Staaten Dauer: 14 Sept. 2009 → 16 Sept. 2009 |
Publikationsreihe
| Name | ICSC 2009 - 2009 IEEE International Conference on Semantic Computing |
|---|
Abstract
State-of-the-art systems for generic concept detection rely on low-level features, and in some cases additionally on features based on face detection, optical character recognition and/or speech recognition. In this paper, an approach for the task of semantic video retrieval is presented that systematically utilizes results of specialized object detectors. Using these object detectors trained on separate public data sets, object-based features are generated by assembling detection results to object sequences. A shot-based confidence score as well as further features, such as position, frame coverage and movement, are computed for each object class. Experimental results on TRECVID test data show significant improvements in terms of retrieval performance not only for the object classes, but also in particular for a large number of indirectly related concepts.
ASJC Scopus Sachgebiete
- Informatik (insg.)
- Theoretische Informatik und Mathematik
- Informatik (insg.)
- Software
- Ingenieurwesen (insg.)
- Elektrotechnik und Elektronik
Zitieren
- Standard
- Harvard
- Apa
- Vancouver
- BibTex
- RIS
ICSC 2009 : 2009 IEEE International Conference on Semantic Computing. 2009. S. 109-115 5298597 (ICSC 2009 - 2009 IEEE International Conference on Semantic Computing).
Publikation: Beitrag in Buch/Bericht/Sammelwerk/Konferenzband › Aufsatz in Konferenzband › Forschung › Peer-Review
}
TY - GEN
T1 - Improving semantic video retrieval via object-based features
AU - Mühling, Markus
AU - Ewerth, Ralph
AU - Freisleben, Bernd
PY - 2009/10/30
Y1 - 2009/10/30
N2 - State-of-the-art systems for generic concept detection rely on low-level features, and in some cases additionally on features based on face detection, optical character recognition and/or speech recognition. In this paper, an approach for the task of semantic video retrieval is presented that systematically utilizes results of specialized object detectors. Using these object detectors trained on separate public data sets, object-based features are generated by assembling detection results to object sequences. A shot-based confidence score as well as further features, such as position, frame coverage and movement, are computed for each object class. Experimental results on TRECVID test data show significant improvements in terms of retrieval performance not only for the object classes, but also in particular for a large number of indirectly related concepts.
AB - State-of-the-art systems for generic concept detection rely on low-level features, and in some cases additionally on features based on face detection, optical character recognition and/or speech recognition. In this paper, an approach for the task of semantic video retrieval is presented that systematically utilizes results of specialized object detectors. Using these object detectors trained on separate public data sets, object-based features are generated by assembling detection results to object sequences. A shot-based confidence score as well as further features, such as position, frame coverage and movement, are computed for each object class. Experimental results on TRECVID test data show significant improvements in terms of retrieval performance not only for the object classes, but also in particular for a large number of indirectly related concepts.
KW - Object detection
KW - Semantic concept detection
KW - Video retrieval
UR - http://www.scopus.com/inward/record.url?scp=73449126520&partnerID=8YFLogxK
U2 - 10.1109/ICSC.2009.85
DO - 10.1109/ICSC.2009.85
M3 - Conference contribution
AN - SCOPUS:73449126520
SN - 9780769538006
T3 - ICSC 2009 - 2009 IEEE International Conference on Semantic Computing
SP - 109
EP - 115
BT - ICSC 2009
T2 - ICSC 2009 - 2009 IEEE International Conference on Semantic Computing
Y2 - 14 September 2009 through 16 September 2009
ER -