Abstract
Contextual information can be used to help object detection in video and images, or to categorize text. In this work we demonstrate how the Latent Variable Model, expressed as a Factor Graph in Reduced Normal Form, can manage contextual information to support a scene understanding task. In an unsupervised scenario our model learns how various objects can coexist, by associating object variables to a latent Bayesian cluster. The model, that is implemented using probabilistic message propagation, can be used to correct or to assign labels to new images.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Oliva, A., Torralba, A.: The role of context in object recognition. Trends Cogn. Sci. 11, 520–527 (2007)
Mottaghi, R., Chen, X., Liu, X., Cho, N.G., Lee, S.W., Fidler, S., Urtasun, R., Yuille, A.: The role of context for object detection and semantic segmentation in the wild. In: 2014 IEEE Conference on Computer Vision and Pattern Recognition, pp. 891–898 (2014)
Torralba, A.: Contextual priming for object detection. Int. J. Comput. Vis. 53(2), 169–191 (2003)
Jin, Y., Geman, S.: Context and hierarchy in a probabilistic image model. In: 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2006), vol. 2, pp. 2145–2152 (2006)
Galleguillos, C., Rabinovich, A., Belongie, S.: Object categorization using co-occurrence, location and appearance. In: IEEE Conference on Computer Vision and Pattern Recognition, 2008. CVPR 2008. pp. 1–8. IEEE (2008)
Heitz, G., Koller, D.: Learning Spatial Context: Using Stuff to Find Things, pp. 30–43. Springer, Berlin Heidelberg (2008)
Yao, B., Li, F.: Recognizing human-object interactions in still images by modeling the mutual context of objects and human poses. IEEE Trans. Pattern Anal. Mach. Intell. 34(9), 1691–1703 (2012)
Murphy, K.P.: Machine Learning: A Probabilistic Perspective (Adaptive Computation and Machine Learning series). The MIT Press (2012)
Choi, J.M., Torralba, A., Willsky, A.S.: A tree.based context model for object recognition. IEEE Trans. 34, 240–252 (2012)
Lin, T., Maire, M., Belongie, S.J., Bourdev, L.D., Girshick, R.B., Hays, J., Perona, P., Ramanan, D., Dollár, P., Zitnick, C.L.: Microsoft COCO: common objects in context. In: CoRR, vol. abs/1405.0312 (2014)
Loeliger, H.A.: An introduction to factor graphs. IEEE Signal Process. Mag. vol. 21, pp. 28–41 (2004)
Palmieri, F.A.N.: A comparison of algorithms for learning hidden variables in bayesian factor graphs in reduced normal form. IEEE Trans. Neural Netw. Learn. Syst. 27, 2242–2255 (2016)
Buonanno, A., Palmieri, F.A.N.: Simulink implementation of belief propagation in normal factor graphs. In: Proceedings of the 24th Workshop on Neural Networks, WIRN 2014, May 15–16, Vietri sul Mare, Salerno, Italy (2014)
Buonanno, A., Palmieri, F.A.N.: Towards building deep networks with bayesian factor graphs (2015). http://arxiv.org/abs/1502.04492
Buonanno, A., Palmieri, F.A.N.: Two-dimensional multi-layer factor graphs in reduced normal form. In: Proceedings of the International Joint Conference on Neural Networks, IJCNN2015, July 12–17, 2015, Killarney, Ireland (2015)
Kschischang, F.R., Frey, B., Loeliger, H.: Factor graphs and the sum-product algorithm. IEEE Trans. Inform. Theory 47, 498–519 (2001)
Koller, D., Friedman, N.: Probabilistic Graphical Models: Principles and Techniques. MIT Press (2009)
Palmieri, F.A.N., Buonanno, A.: Discrete independent component analysis (dica) with belief propagation. In: Proceedings of IEEE Machine Learning for Signal Procesing Conference, MLSP2015, Sept. 17–20, Boston, US (2015)
Buonanno, A., di Grazia, L., Palmieri, F.A.N.: Bayesian clustering on images with factor graphs in reduced normal form. In: Proceedings of the 25th Workshop on Neural Networks, WIRN 2015, May 20–22, Vietri sul Mare, Salerno, Italy (2015)
Cover, T.M., Thomas, J.A.: Elements of Information Theory. Wiley (2006)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer International Publishing AG, part of Springer Nature
About this chapter
Cite this chapter
Buonanno, A., Iadicicco, P., Di Gennaro, G., Palmieri, F.A.N. (2019). Context Analysis Using a Bayesian Normal Graph. In: Esposito, A., Faundez-Zanuy, M., Morabito, F., Pasero, E. (eds) Neural Advances in Processing Nonlinear Dynamic Signals. WIRN 2017 2017. Smart Innovation, Systems and Technologies, vol 102. Springer, Cham. https://doi.org/10.1007/978-3-319-95098-3_8
Download citation
DOI: https://doi.org/10.1007/978-3-319-95098-3_8
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-95097-6
Online ISBN: 978-3-319-95098-3
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)