Abstract
The context-based concept fusion (CBCF) is increasingly used in video semantic indexing, which uses various relations among different concepts to refine the original detection results. In this paper, we present a CBCF method called Temporal-Spatial Node Balance algorithm (TSNB). This method is based on a physical model, in which the concepts are regard as nodes and the relations are regard as forces. Then all the spatial and temporal relations and the moving cost of the nodes will be balanced. This method is intuitive and observable to explain a concept how to influence others or be influenced by others. And it uses both the spatial and temporal information to describe the semantic structure of the video. We use TSNB algorithm on the datasets of TRECVid 2005-2010. The results show that this method outperforms all the existed works as we know. Besides, it is faster.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Lew, M.S., et al.: Content-based multimedia information retrieval: State of the art and challenges. ACM Trans. on Mult. Comp. Comm. Appl. 2 (2006)
Smeaton, A.F., et al.: Evaluation campaigns and trecvid. In: MIR 2006 (2006)
Ramesh Naphade, M., et al.: Factor graph framework for semantic video indexing. IEEE Trans. on CSVT 12 (2002)
Weng, M.F., et al.: Multi-cue fusion for semantic video indexing. In: MM 2008 (2008)
Zha, Z.J., et al.: Refining video annotation by exploiting pairwise concurrent relation. In: MM 2007 (2007)
Zheng, Y., et al.: Semantic video indexing by fusing explicit and implicit context spaces. In: MM 2010 (2010)
Zha, Z.J., et al.: Building a comprehensive ontology to refine video concept detection. In: MIR 2007 (2007)
Fan, J., et al.: Incorporating concept ontology for hierarchical video classification, annotation, and visualization. IEEE Trans. on MM 9 (2007)
Gu, Z., et al.: Multi-layer multi-instance learning for video concept detection. IEEE Trans. on MM 10 (2008)
Mylonas, P., et al.: Using visual context and region semantics for high-level concept detection. IEEE Trans. on MM 11 (2009)
Wei, X.Y., et. al.: Exploring inter-concept relationship with context space for semantic video indexing. In: CIVR 2009 (2009)
Smith, J., et al.: Multimedia semantic indexing using model vectors. In: ICME 2003 (2003)
Jiang, W., et al.: Context-based concept fusion with boosted conditional random fields. In: ICASSP 2007 (2007)
Jiang, Y.G., et al.: Domain adaptive semantic diffusion for large scale context-based video annotation. In: ICCV 2009 (2009)
Golub, G., et al.: A hessenberg-schur method for the problem ax + xb= c. IEEE Trans. on AC 24 (1979)
(Trecvid), http://www-nlpir.nist.gov/projects/trecvid/
Naphade, M., et al.: Large-scale concept ontology for multimedia. IEEE Multimedia (2006)
Yanagawa, A., et al.: Columbia university’s baseline detectors for 374 lscom semantic visual concepts. Columb. Univ. ADVENT Techn. Report (2007)
Jiang, Y.G., et al.: Vireo-374: Keypoint-based lscom semantic concept detectors, http://vireo.cs.cityu.edu.hk/research/vireo374/
Jiang, Y.G., et al.: CU-VIREO374: Fusing Columbia374 and VIREO374 for Large Scale Semantic Concept Detection. Technical report, Columb. Univ. ADVENT #223-2008-1 (2008)
Yilmaz, E., et al.: Estimating average precision with incomplete and imperfect judgments. In: CIKM 2006 (2006)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Geng, J., Miao, Z., Chi, H. (2013). Temporal-Spatial Refinements for Video Concept Fusion. In: Lee, K.M., Matsushita, Y., Rehg, J.M., Hu, Z. (eds) Computer Vision – ACCV 2012. ACCV 2012. Lecture Notes in Computer Science, vol 7726. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-37431-9_42
Download citation
DOI: https://doi.org/10.1007/978-3-642-37431-9_42
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-37430-2
Online ISBN: 978-3-642-37431-9
eBook Packages: Computer ScienceComputer Science (R0)