Detail publikace

TRECVID 2007 by the Brno Group

HEROUT Adam, BERAN Vítězslav, HRADIŠ Michal, POTÚČEK Igor, ZEMČÍK Pavel a CHMELAŘ Petr. TRECVID 2007 by the Brno Group. In: Proceedings of TRECVID 2007. Gaithersburg: National Institute of Standards and Technology, 2008, s. 1-6. ISBN 978-1-59593-780-3.
Název česky
TRECVID 2007 by the Brno Group
Typ
článek ve sborníku konference
Jazyk
angličtina
Autoři
Abstrakt

High Level Feature Extraction
    1. The runs:
            - A_brU_1 - features extracted from each frame; SVM per-frame classifier trained on frames in each
                shot; simple decision tree judging shots based on per-frame results
            - A_brV_2 - same as A_brU_1, but SVM trained on all training data (the first run divided the training
                data to training and cross-validation datasets), with SVM configured from the previous run
    2. Significant differences between the runs:
            - As expected, the second run performed generally better, in some cases notably better (which is slightly
                surprising, because besides the amount of training data, there was no change)
    3. Contribution of each component:
            - The low-level features appear to be good enough, though their number is relatively large and having
                more time we would experiment with reduction of the feature vector size (now 572 low level features)
            - We considered using some mid-level features based on existing solutions the group has, such as face
                detection, car detection, etc., but for time constraints did not employ these in the feature vector
            - The per-frame classification seems to suffer greatly from mis-annotated frames (whole shots are
                considered to share the same annotation information in our system) and could be the weakest point of
                the system
            - The per-shot decision making seems to be sufficient given the data coming from the per-shot
                classification
    4. Overall comments:
            - see further in the paper

Shot Boundary Detection
We describe our approach to cut detection where we use AdaBoost boosting algorithm to create a detection classifier
from a large set of features which are based on few simple frame distance measures. First, we introduce the reasons
which led us to use AdaBoost algorithm, then we describe the set of features and we also discuss the achieved result.
Finally, we present the possible future improvements to the current approach.

Rok
2008
Strany
1-6
Sborník
Proceedings of TRECVID 2007
Konference
2007 TRECVID Workshop, NIST, Gaithersburg, Maryland, US
ISBN
978-1-59593-780-3
Vydavatel
National Institute of Standards and Technology
Místo
Gaithersburg, US
BibTeX
@INPROCEEDINGS{FITPUB8827,
   author = "Adam Herout and V\'{i}t\v{e}zslav Beran and Michal Hradi\v{s} and Igor Pot\'{u}\v{c}ek and Pavel Zem\v{c}\'{i}k and Petr Chmela\v{r}",
   title = "TRECVID 2007 by the Brno Group",
   pages = "1--6",
   booktitle = "Proceedings of TRECVID 2007",
   year = 2008,
   location = "Gaithersburg, US",
   publisher = "National Institute of Standards and Technology",
   ISBN = "978-1-59593-780-3",
   language = "english",
   url = "https://www.fit.vut.cz/research/publication/8827"
}
Nahoru