Details
| Original language | English |
|---|---|
| Title of host publication | 2010 TREC Video Retrieval Evaluation Notebook Papers and Slides |
| Publication status | Published - 2010 |
| Externally published | Yes |
| Event | TREC Video Retrieval Evaluation, TRECVID 2010 - Gaithersburg, MD, United States Duration: 15 Nov 2010 → 17 Nov 2010 |
Abstract
In this paper, we summarize our results for the semantic indexing task at TRECVID 2010. Last year, we showed that the use of object detection results as an additional input for SVM-based concept classifiers improved the overall performance. This year, we investigated whether a state-of-the-art bag-of-visual-words (BoW) approach can also be improved by adding object-based features. In this context, Multiple Kernel Learning (MKL) was applied to find the best feature weighting. The experiments revealed that the supplementation of BoW-based features with object-based features significantly improved the concept detection performance. Furthermore, we showed that a more uniform distribution of kernel weights using l2-norm MKL gained better results. Altogether, our best run achieved a mean inferred average precision of 6.96% and we submitted the best results for the concepts "vehicle" and "ground_vehicle".
ASJC Scopus subject areas
- Computer Science(all)
- Computer Graphics and Computer-Aided Design
- Computer Science(all)
- Computer Vision and Pattern Recognition
- Computer Science(all)
- Human-Computer Interaction
- Computer Science(all)
- Software
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
2010 TREC Video Retrieval Evaluation Notebook Papers and Slides. 2010.
Research output: Chapter in book/report/conference proceeding › Conference contribution › Research › peer review
}
TY - GEN
T1 - University of Marburg at TRECVID 2010
T2 - TREC Video Retrieval Evaluation, TRECVID 2010
AU - Mühling, Markus
AU - Ewerth, Ralph
AU - Freisleben, Bernd
PY - 2010
Y1 - 2010
N2 - In this paper, we summarize our results for the semantic indexing task at TRECVID 2010. Last year, we showed that the use of object detection results as an additional input for SVM-based concept classifiers improved the overall performance. This year, we investigated whether a state-of-the-art bag-of-visual-words (BoW) approach can also be improved by adding object-based features. In this context, Multiple Kernel Learning (MKL) was applied to find the best feature weighting. The experiments revealed that the supplementation of BoW-based features with object-based features significantly improved the concept detection performance. Furthermore, we showed that a more uniform distribution of kernel weights using l2-norm MKL gained better results. Altogether, our best run achieved a mean inferred average precision of 6.96% and we submitted the best results for the concepts "vehicle" and "ground_vehicle".
AB - In this paper, we summarize our results for the semantic indexing task at TRECVID 2010. Last year, we showed that the use of object detection results as an additional input for SVM-based concept classifiers improved the overall performance. This year, we investigated whether a state-of-the-art bag-of-visual-words (BoW) approach can also be improved by adding object-based features. In this context, Multiple Kernel Learning (MKL) was applied to find the best feature weighting. The experiments revealed that the supplementation of BoW-based features with object-based features significantly improved the concept detection performance. Furthermore, we showed that a more uniform distribution of kernel weights using l2-norm MKL gained better results. Altogether, our best run achieved a mean inferred average precision of 6.96% and we submitted the best results for the concepts "vehicle" and "ground_vehicle".
UR - http://www.scopus.com/inward/record.url?scp=84905198846&partnerID=8YFLogxK
M3 - Conference contribution
BT - 2010 TREC Video Retrieval Evaluation Notebook Papers and Slides
Y2 - 15 November 2010 through 17 November 2010
ER -