Infrequent concept pairs detection in multimedia documents
Pages 435 - 438
Abstract
Single visual concept detection in videos is a hard task, especially for infrequent concepts or for those difficult to model. This question becomes even more difficult in the case of concept pairs. Two main directions may tackle this problem: 1) combine the predictions of their corresponding detectors in a way which is similar to usual information retrieval, or 2) build supervised learners for these pairs of concepts by generating annotations based on the occurrences of the two individual concepts. Each of these approaches have advantages and drawbacks. We evaluated them in the context of the concept pair detection subtask of the TRECVid 2013 semantic indexing (SIN) task and found that information retrieval-like fusions of concept detection scores outperforms the learning approaches. The described methods outperform the best official result of the evaluation campaign cited previously, by 9% in terms of relative improvement on MAP.
References
[1]
R. Aly, D. Hiemstra, A. de Vries, and F. de Jong. A probabilistic ranking framework using unobservable binary events for video search. In 7th ACM International Conference on Content-based Image and Video Retrieval, CIVR 2008, pages 349--358, New York, NY, USA, July 2008. ACM.
[2]
S. Ayache and G. Quénot. Video corpus annotation using active learning. In Proceedings of the IR research, ECIR'08, pages 187--198, Berlin, Heidelberg, 2008. Springer-Verlag.
[3]
N. Ballas, B. Labbé, A. Shabou, H. Le Borgne, P. Gosselin, M. Redi, B. Merialdo, H. Jégou, J. Delhumeau, R. Vieux, B. Mansencal, J. Benois-Pineau, S. Ayache, A. Hamadi, B. Safadi, F. Thollard, N. Derbas, G. Quénot, H. Bredin, M. Cord, B. Gao, C. Zhu, Y. tang, E. Dellandrea, C.-E. Bichot, L. Chen, A. BenoÃőt, P. Lambert, T. Strat, J. Razik, S. Paris, H. Glotin, T. Ngoc Trung, D. Petrovska Delacrétaz, G. Chollet, A. Stoian, and M. Crucianu. IRIM at TRECVID 2012: Semantic Indexing and Instance Search. In Proc. TRECVID Workshop, Gaithersburg, MD, USA, 2012.
[4]
S.-F. Chang, W. Hsu, W. Jiang, L. Kennedy, D. Xu, A. Yanagawa, and E. Zavesky. Columbia university trecvid-2006 video search and high-level feature extraction. in proc. trecvid workshop. In In Proc. TRECVID Workshop, 2006.
[5]
X. Li, C. G. M. Snoek, M. Worring, and A. Smeulders. Harvesting social images for bi-concept search. Multimedia, IEEE Transactions on, 14(4):1091--1104, 2012.
[6]
X. Li, D. Wang, J. Li, and B. Zhang. Video search in concept subspace: A text-like paradigm. In Proc. of CIVR, 2007.
[7]
J. Platt. Probabilistic outputs for support vector machines and comparison to regularize likelihood methods. In A. Smola, P. Bartlett, B. Schoelkopf, and D. Schuurmans, editors, Advances in Large Margin Classifiers, pages 61--74, 2000.
[8]
B. Safadi and G. Quénot. Evaluations of multi-learner approaches for concept indexing in video documents. In RIAO, pages 88--91, 2010.
[9]
G. Salton, E. A. Fox, and H. Wu. Extended boolean information retrieval. Commun. ACM, 26(11):1022--1036, Nov. 1983.
[10]
A. F. Smeaton. Independence of contributing retrieval strategies in data fusion for effective information retrieval. In Proceedings of the 20th Annual BCS-IRSG conference on Information Retrieval Research, IRSG'98, pages 12--12, Swinton, UK, UK, 1998. British Computer Society.
[11]
C. G. Snoek, B. Huurnink, L. Hollink, M. de Rijke, G. Schreiber, and M. Worring. Adding semantics to detectors for video retrieval. Trans. Multi., 9(5):975--986, Aug. 2007.
[12]
G. Wang and D. A. Forsyth. Joint learning of visual attributes, object classes and visual saliency. In ICCV'09, pages 537--544, 2009.
[13]
X.-Y. Wei, Y.-G. Jiang, and C.-W. Ngo. Concept-driven multi-modality fusion for video search. Circuits and Systems for Video Technology, IEEE Transactions on, 21(1):62--73, 2011.
[14]
R. Yan and A. G. Hauptmann. The combination limit in multimedia retrieval. In In Proceedings of the eleventh ACM international conference on Multimedia, pages 339--342, 2003.
Index Terms
- Infrequent concept pairs detection in multimedia documents
Recommendations
A comparative study for multiple visual concepts detection in images and videos
Automatic indexing of images and videos is a highly relevant and important research area in multimedia information retrieval. The difficulty of this task is no longer something to prove. Most efforts of the research community have been focusing, in the ...
Extended conceptual feedback for semantic multimedia indexing
In this paper, we consider the problem of automatically detecting a large number of visual concepts in images or video shots. State of the art systems generally involve feature (descriptor) extraction, classification (supervised learning) and fusion ...
A Comprehensive Study of Feature Representations for Semantic Concept Detection
ICSC '11: Proceedings of the 2011 IEEE Fifth International Conference on Semantic ComputingIn this paper, we study the performance of global features and local features for the semantic concept detection problem, which is a crucial task for video indexing and retrieval applications. We have performed a comprehensive evaluation of these ...
Comments
Information & Contributors
Information
Published In
April 2014
564 pages
ISBN:9781450327824
DOI:10.1145/2578726
- Conference Chairs:
- Mohan Kankanhalli,
- Stefan Rueger,
- R. Manmatha,
- General Chairs:
- Joemon Jose,
- Keith van Rijsbergen
Copyright © 2014 ACM.
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]
In-Cooperation
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 01 April 2014
Check for updates
Author Tags
Qualifiers
- Tutorial
- Research
- Refereed limited
Conference
ICMR '14
Acceptance Rates
ICMR '14 Paper Acceptance Rate 21 of 111 submissions, 19%;
Overall Acceptance Rate 254 of 830 submissions, 31%
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 46Total Downloads
- Downloads (Last 12 months)0
- Downloads (Last 6 weeks)0
Reflects downloads up to 23 Dec 2024
Other Metrics
Citations
View Options
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in