A General Bayesian Multilinear Analysis Framework for Human Behaviour Recognition
Funding: 2012: $133,000
2013: $120,000
2014: $125,000
Funding or Partner Organisation: Australian Research Council (Other funds for ARC projects)
Australian Research Council (ARC Discovery Projects)
Birkbeck College
Start year: 2012
Summary: This project will develop a Bayesian multilinear analysis framework for the vast quantities of images obtained from surveillance videos. The analysis will focus on recognising and recording behaviours in order to build a database of the activities in the area under surveillance. This database will be used to combat crime and terrorism and to give warnings of hazardous situations such as overcrowding, jaywalking or trespassing in areas such as railway tracks. The advantages of the Bayesian approach are that it is logically well founded and that it makes the best use of the available information. The results will enhance Australia's key infrastructures and help maintain Australia's leading role in machine learning and computer vision.
Publications:
Li, J & Tao, D 2013, 'A Bayesian Hierarchical Factorization Model for Vector Fields.', IEEE Trans. Image Process., vol. 22, no. 11, pp. 4510-4521.
View/Download from: Publisher's site
Li, J & Tao, D 2013, 'Exponential Family Factors for Bayesian Factor Analysis.', IEEE Trans. Neural Networks Learn. Syst., vol. 24, no. 6, pp. 964-976.
View/Download from: Publisher's site
Li, J & Tao, D 2013, 'Simple Exponential Family PCA.', IEEE Trans. Neural Networks Learn. Syst., vol. 24, no. 3, pp. 485-497.
View/Download from: Publisher's site
Luo, Y, Tao, D, Xu, C, Xu, C, Liu, H & Wen, Y 2013, 'Multiview Vector-Valued Manifold Regularization for Multilabel Image Classification.', IEEE Trans. Neural Networks Learn. Syst., vol. 24, no. 5, pp. 709-722.
View/Download from: Publisher's site
Song, M, Tao, D, Sun, S, Chen, C & Bu, J 2013, 'Joint Sparse Learning for 3-D Facial Expression Generation.', IEEE Trans. Image Process., vol. 22, no. 8, pp. 3283-3295.
View/Download from: Publisher's site
Zhang, C & Tao, D 2013, 'Risk bounds of learning processes for Lévy processes.', J. Mach. Learn. Res., vol. 14, no. 1, pp. 351-376.
Zhang, K, Gao, X, Tao, D & Li, X 2013, 'Single Image Super-Resolution With Multiscale Similarity Learning.', IEEE Trans. Neural Networks Learn. Syst., vol. 24, no. 10, pp. 1648-1659.
View/Download from: Publisher's site
Zhang, L, Zhang, L, Tao, D & Huang, X 2013, 'Tensor Discriminative Locality Alignment for Hyperspectral Image Spectral-Spatial Feature Extraction.', IEEE Trans. Geosci. Remote. Sens., vol. 51, no. 1, pp. 242-256.
View/Download from: Publisher's site
Zhen, X, Shao, L, Tao, D & Li, X 2013, 'Embedding Motion and Structure Features for Action Recognition.', IEEE Trans. Circuits Syst. Video Technol., vol. 23, no. 7, pp. 1182-1190.
View/Download from: Publisher's site
Geng, B, Tao, D, Xu, C, Yang, L & Hua, X-S 2012, 'Ensemble Manifold Regularization.', IEEE Trans. Pattern Anal. Mach. Intell., vol. 34, no. 6, pp. 1227-1233.
View/Download from: Publisher's site
Li, J, Tao, D & Li, X 2012, 'A probabilistic model for image representation via multiple patterns.', Pattern Recognit., vol. 45, no. 11, pp. 4044-4053.
View/Download from: Publisher's site
Su, Y, Gao, X, Li, X & Tao, D 2012, 'Multivariate Multilinear Regression.', IEEE Trans. Syst. Man Cybern. Part B, vol. 42, no. 6, pp. 1560-1573.
View/Download from: Publisher's site
Tian, X, Tao, D & Rui, Y 2012, 'Sparse transfer learning for interactive video search reranking.', ACM Trans. Multim. Comput. Commun. Appl., vol. 8, no. 3, pp. 26:1-26:1.
View/Download from: Publisher's site
Wang, M, Li, H, Tao, D, Lu, K & Wu, X 2012, 'Multimodal Graph-Based Reranking for Web Image Search.', IEEE Trans. Image Process., vol. 21, no. 11, pp. 4649-4661.
View/Download from: Publisher's site
Yu, J, Cheng, J & Tao, D 2012, 'Interactive cartoon reusing by transfer learning.', Signal Process., vol. 92, no. 9, pp. 2147-2158.
View/Download from: Publisher's site
Zhang, K, Gao, X, Tao, D & Li, X 2012, 'Single Image Super-Resolution With Non-Local Means and Steering Kernel Regression.', IEEE Trans. Image Process., vol. 21, no. 11, pp. 4544-4556.
View/Download from: Publisher's site
Zhang, K, Mu, G, Yuan, Y, Gao, X & Tao, D 2012, 'Video super-resolution with 3D adaptive normalized convolution.', Neurocomputing, vol. 94, pp. 140-151.
View/Download from: Publisher's site
Zhou, T, Tao, D & Wu, X 2012, 'Compressed labeling on distilled labelsets for multi-label learning.', Mach. Learn., vol. 88, no. 1-2, pp. 69-126.
View/Download from: Publisher's site
He, L, Tao, D, Li, X & Gao, X 1970, 'Sparse representation for blind image quality assessment.', CVPR, IEEE Conference on Computer Vision and Pattern Recognition, IEEE Computer Society, Providence, USA, pp. 1146-1153.
View/Download from: Publisher's site
Liu, X, Song, M, Zhang, L, Tao, D, Bu, J & Chen, C 1970, 'Pedestrian detection using a mixture mask model.', ICNSC, International Conference on Networking, Sensing and Control, IEEE, Beijing, China, pp. 271-276.
View/Download from: Publisher's site
Zhang, K, Gao, X, Tao, D & Li, X 1970, 'Multi-scale dictionary for single image super-resolution.', CVPR, IEEE Conference on Computer Vision and Pattern Recognition, IEEE Computer Society, Providence, USA, pp. 1114-1121.
View/Download from: Publisher's site
Zhou, T & Tao, D 1970, '1-bit Hamming compressed sensing.', ISIT, IEEE International Symposium on Information Theory, IEEE, Cambridge, USA, pp. 1862-1866.
View/Download from: Publisher's site
Zhou, T & Tao, D 1970, 'Bilateral Random Projections', IEEE International Symposium on Information Theory - Proceedings, IEEE International Symposium on Information Theory, IEEE, Cambridge, USA, pp. 1286-1290.
View/Download from: Publisher's site
Keywords: Machine LearningComputer VisionVideo SurveillanceBayesian Analysis
FOR Codes: Pattern Recognition and Data Mining, Intelligence, Computer Vision, Electronic Information Storage and Retrieval Services, Film and Video Services (excl. Animation and Computer Generated Imagery), Data mining and knowledge discovery, Intelligence, surveillance and space, Radio, television, film and video services