Abstract
Automatically assigning relevant text labels to 3D model is an important problem. For this task we propose a semi-supervised measure learning method. Labels of 3D models are predicted using a graph-based semi-supervised method to exploit labeled and unlabeled 3D models. In this manner, we can get semantic confidence of labels. An improved relevant component analysis method is also proposed to learn a distance measure based on label’s semantic confidence. A novel approach based on the semantic confidence and the distance is applied on multi-semantic automatic annotation task. We investigate the performance of our method and compare to existing work. The experimental results demonstrate that the method is more accurate when a small amount of labels were given.
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
Philip, S., Patrick, M., Michael, K.: The Princeton Shape Benchmark. Shape Modeling International, 388–399 (2004)
Chen, D.-Y., Tian, X.-P., Shen, Y.-T.: On visual similarity based 3D model retrieval. Eurographics, 22–26 (2003)
Paquet, E., Murching, A., Naveen, T., Tabatabai, A., Rioux, M.: Description of shape information for 2-D and 3-D objects. Signal Process. Image Commun., 103–122 (2000)
Min, P., Kazhdan, M., Funkhouser, T.: A Comparison of Text and Shape Matching for Retrieval of Online 3D Models. In: Heery, R., Lyon, L. (eds.) ECDL 2004. LNCS, vol. 3232, pp. 209–220. Springer, Heidelberg (2004)
Meng, Z., Atta, B.: Semantic-associative visual content labeling and retrieval: A multimodal approach. Signal Processing: Image Communication, 569–582 (2007)
Funkhouser, T., Min, P., Kazhdan, M., Chen, J., Halderman, A., Dobkin, D., Jacobs, D.: A Search Engine for 3D Models. ACM Transactions on Graphics 22(1), 83–105 (2003)
Datta, R., Ge, W., Li, J.: Toward bridging the annotation-retrieval gap in image search by a generative modeling approach. In: Proceedings of the 14th Annual ACM International Conference on Multimedia, Santa Barbara, CA, USA, pp. 23–27 (2006)
Zhou, D., Bousquet, O., Lal, T., Weston, J., Scholkopf, B.: Ranking on data manifolds. In: Proceedings of the 18th Annual Conference on Neural Information Processing System, pp. 169–176 (2003)
Shental, N., Hertz, T., Weinshall, D., Pavel, M.: Adjustment Learning and Relevant Component Analysis. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002, Part IV. LNCS, vol. 2353, pp. 776–790. Springer, Heidelberg (2002)
Heczko, M., Keim, D., Saupe, D.: Methods for similarity search on 3D databases. Datenbank-Spektrum, 54–63 (2002) (in German)
Hou, S., Lou, K., Ramanik: SVM based semantic clustering and retrieval of a 3D model database. Journal of Computer Aided Design and Application, 155–164 (2005)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Tian, F., Shen, Xk., Liu, Xm., Zhou, K. (2011). Semi-supervised Metric Learning for 3D Model Automatic Annotation. In: Jin, D., Lin, S. (eds) Advances in Multimedia, Software Engineering and Computing Vol.1. Advances in Intelligent and Soft Computing, vol 128. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-25989-0_16
Download citation
DOI: https://doi.org/10.1007/978-3-642-25989-0_16
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-25988-3
Online ISBN: 978-3-642-25989-0
eBook Packages: EngineeringEngineering (R0)