=Paper=
{{Paper
|id=Vol-1174/CLEF2008wn-VideoCLEF-PereaOrtegaEt2008
|storemode=property
|title=SINAI at VideoCLEF 2008
|pdfUrl=https://ceur-ws.org/Vol-1174/CLEF2008wn-VideoCLEF-PereaOrtegaEt2008.pdf
|volume=Vol-1174
|dblpUrl=https://dblp.org/rec/conf/clef/Perea-OrtegaMMDU08
}}
==SINAI at VideoCLEF 2008==
https://ceur-ws.org/Vol-1174/CLEF2008wn-VideoCLEF-PereaOrtegaEt2008.pdf
SINAI at VideoCLEF 2008
José M. Perea-Ortega, Arturo Montejo-Ráez, M. Teresa Martı́n-Valdivia,
Manuel C. Dı́az-Galiano, L. Alfonso Ureña-López
SINAI Research Group. Computer Science Department. University of Jaén
Campus Las Lagunillas, Ed. A3, E-23071, Jaén, Spain
{jmperea,amontejo,maite,mcdiaz,laurena}@ujaen.es
Abstract
This paper describes the first participation of the SINAI research group in the Video-
CLEF 2008 track. We have only submitted runs for the classification task on Dutch
and English languages. Our approach has consisted in the use of a particular Informa-
tion Retrieval system as classification architecture, using the speech transcriptions as
textual queries and generating textual corpus for each topic class. In order to generate
this textual corpus we have used the Google1 search engine. The experiments show
that an IR system can perform well as classifier of multilingual videos, using their
speech transcriptions and obtaining good results.
Categories and Subject Descriptors
H.3 [Information Storage and Retrieval]: H.3.1 Content Analysis and Indexing; H.3.3 Infor-
mation Search and Retrieval; H.3.4 Systems and Software
General Terms
Measurement, Performance, Experimentation
Keywords
Content-based retrieval, Multilingual video classification, Information Retrieval, VideoCLEF
1 Introduction
This paper describes the first participation of the SINAI2 research group from University of Jaén
in the VideoCLEF 2008 campaign. VideoCLEF is a new track for Cross Language Evaluation
Forum (CLEF) 2008 and it aims to develop and evaluate tasks in processing video content in
a multilingual environment. The overall objective is to combine and extend these subtasks and
perform completely automatic generation of RSS feeds specific to a particular information need
and personalized to a particular language preference. The main task for VideoCLEF 2008 involves
assigning topic class labels to videos of television episodes3 .
The aim of our first participation in VideoCLEF has been the study of the problem of this
task, and the development of a basic architecture which approaches it. We have some experience
in the field of multimedia video retrieval [1] and in image retrieval [2, 3, 4].
1 http://www.google.com
2 http://sinai.ujaen.es
3 http://ilps.science.uva.nl/Vid2RSS/Vid2RSS08/Vid2RSS08.html
Figure 1: Basic architecture of the SINAI video classifier
This paper is organized as follows: section 2 describes the whole system. Then, in the section 3
experiments, results and resources employed are described. Finally, in the section 4, the conclusions
are presented.
2 System description
The overall architecture of our automatic video classifier is based on the use of a particular IR
system as classification system. In our experiments we have used Lemur4 as IR system.
In our approach we have two main processes:
• Generating a text-corpus per class. We have generated a textual corpus per topic class.
This corpus corresponds to the ten top retrieved results by Google, using the topic word (e.g.
Architecture) as search query. The use of Google has been found useful in other tasks like
Robust Retrieval[5]. These results have been combined into one single document. Therefore,
a document per class is obtained after this process. Each document per class is indexed
by means of IR system. This index will be used for retrieving the speech transcriptions
preprocessed of each test video (textual queries).
• Generating a text-query per video. We have used the textual information available from
Automatic Speech Recognition (ASR) output in order to generate the textual queries for each
test video. This data has been preprocessed using the Dutch stemmer from Snowball5 for
Dutch language and Porter stemmer [6] for English. We have also discarded the stop-words
for both languages.
4 http://www.lemurproject.org
5 http://snowball.tartarus.org/algorithms/dutch/stemmer.html
Experiment Language Using metadata P R F1
SINAI-JEAN-Class-I Dutch no 0.65 0.42 0.51
SINAI-JEAN-Class-I-Trans English no 0.13 0.09 0.10
SINAI-JEAN-Class-II Dutch yes 0.68 0.44 0.53
Table 1: Micro-averaging results
Experiment Language Using metadata P R F1
SINAI-JEAN-Class-I Dutch no 0.91 0.34 0.49
SINAI-JEAN-Class-I-Trans English no 0.68 0.28 0.40
SINAI-JEAN-Class-II Dutch yes 0.89 0.36 0.51
Table 2: Macro-averaging results
For each textual query generated the IR subsystem retrieves the document class more relevant,
using the standard TF·IDF [7] weighting scheme. The Figure 1 shows this basic architecture of
our approach.
3 Experiments and Results
In our first participation in VideoCLEF, we have only submitted three runs for the classification
subtasks. There is one mandatory classification task (classification task I) which uses speech
transcriptions only. We have submitted two runs for this task, one for each language (Dutch
and English). The name of these experiments are SINAI-JEAN-Class-I and SINAI-JEAN-Class-
I-Trans respectively. For the third run we have used the archival metadata supplied (classification
task II), only for Dutch language. This run is identified as SINAI-JEAN-Class-II. The results
using micro-averaged and macro-averaged measures are shown in Tables 1 and 2.
Analyzing the results obtained, we can observe that English language leads to worse results
than Dutch. This could be an expected behavior, due to the lower relevance of this language in the
corpus compared to Dutch. In micro-averaged values, the use of metadata brings slightly better
precision and recall measurements, although in macro-averaged results this improvement is only
present in recall.
3.1 Resources
The ASR transcriptions of video files have been supplied by the organization of VideoCLEF6 . This
video data are Dutch television documentaries and contain Dutch as dominant language, but also
contain a high proportion of spoken English, such as interviewed guests. On the other hand, the
archival metadata resource contains program titles and short descriptions of the content of video
files.
4 Conclusions
We have described here the approach followed by the SINAI research group in its participation
in the VideoCLEF 2008 campaign. Our results show that, despite the simplicity of our system,
transcriptions are a good source of information for video classification. Anyhow, some enhance-
ments on the system can be performed, by selecting additional sources of learning data: we are
working on a system that uses Wikipedia articles too.
6 The data for VideoCLEF 2008 has been provided by The Netherlands Institute of Sound and Vision (Beeld &
Geluid). Thank you also to the University of Twente for providing the speech recognition transcripts.
References
[1] Dı́az-Galiano, M.C., Perea-Ortega, J.M., Martı́n-Valdivia, M.T., Montejo-Ráez, A., Ureña-
López, L.A. SINAI at TRECVID 2007. In Proceedings of the TRECVID 2007 Workshop
(TRECVID 2007), 2007.
[2] Dı́az-Galiano, M.C., Garcı́a-Cumbreras, M.A., Martı́n-Valdivia, M.T., Montejo-Ráez, A.,
Ureña-López, L.A. SINAI at ImageCLEF 2007. In Proceedings of the Cross Language Evalu-
ation Forum (CLEF 2007), 2007.
[3] Dı́az-Galiano, M.C., Garcı́a-Cumbreras, M.A., Martı́n-Valdivia, M.T., Montejo-Ráez, A.,
Ureña-López, L.A. SINAI at ImageCLEF 2006. In Proceedings of the Cross Language Evalu-
ation Forum (CLEF 2006), 2006.
[4] Martı́n-Valdivia, M.T., Garcı́a-Cumbreras, M.A., Dı́az-Galiano, M.C., Ureña-López, L.A., A.
Montejo-Ráez. SINAI at ImageCLEF 2005. In Proceedings of the Cross Language Evaluation
Forum (CLEF 2005), 2005.
[5] F. Martı́nez-Santiago, M.A. Garcı́a-Cumbreras, and Arturo Montejo-Ráez. SINAI at CLEF
2007 Ad Hoc Robust track 2007: Applying google search engine for robust cross-lingual re-
trieval. In Proceedings of the Cross Language Evaluation Forum (CLEF 2007), 2007.
[6] M.F. Porter. An algorithm for suffix stripping. In Program 14, pages 130–137, 1980.
[7] G. Salton and M. J. McGill. Introduction to Modern Information Retrieval. McGraw-Hill,
London, U.K., 1983.