Up   

Projects   

Publication   

Software/Demo   

Interest

• Learning Structured Output Space
• Probabilistic Graphical Models
• Recommender Systems

Current projects

• Recommender systems. The goal is to deliver right services to right users in (near) real time. Most existing work is rather ad-hoc and ignores complex nature of the data. Research topics include discovering hidden patterns, incorporating contexts and side-information, social networks, multiple-domains, product hierarchies, as well as correlations between actors and items. [Publication AusDM'07, UAI'09 ].

  • Recommendation for people with visual impairment. This promises to be extremely challenging, because the recommended information must be (i) highly relevant, (ii) accurate, and (iii) presented in a sequential way, or through speech devices.

• Modelling complex data types. Research topics include data types like ordinal, multiple label, label ranking, or preference graph.  [Publication UAI'09 ]

  • Permutation modelling for rank data (like user preference over products), and learning-to-rank.

• Representation, learning and inference with undirected graphical models. Sub-projects include:

  • Sequential data. This is indeed very rich type of data which we encounter everyday. Issues include feature discovery, segmentation, permutation, collocation and n-grams. One the the extreme is the problem of statistical machine translation, where the output space is theoretially infinite (the target language space).

  • Fast learning and inference for chain and general structures. [Publication CVPR'06, Tech Report'07, PRICAI'08]

  • Hierarchical semi-Markov chains: generalising Markov chains to nested processes. Issues include modeling, parameterisation & efficient inference and learning with near linear complexity. [Publication: NIPS'08, DLSRRA'09 ]

Past projects

• Discriminative methods for activity recognition. Better exploit of rich sensory information for activity recognition. Issues investigated: partial labeling, feature selection & multilevel of semantics. [Publication: PRICAI'08, CVPR'06, ISSNIP'05, NIPS'08 ]

• Vietnamese accent restoration. Fiven an accentless sentence, we need to restore the lost accents (or tonal marks) [Publication; PRICAI'08 ] [Demo].

Publications

2010

• Nonnegative Shared Subspace Learning and Its Application to Social Media Retrieval, S. Gupta, D. Phung, B. Adams, T.T. Truyen and S. Venkatesh, In Proc. of 16th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 25-28 Jul, Washington DC, 2010

• Classification and Pattern Discovery of Mood in Weblogs, T. Nguyen, D. Phung, B. Adams, T. Truyen and S. Venkatesh. In Proc. of Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD), 21-24 June, Hyderabad, India, 2010.

2009

• MCMC for Hierarchical Semi-Markov Conditional Random Fields, Tran The Truyen, Dinh. Q Phung, Svetha Venkatesh and Hung H. Bui. In NIPS'09 Workshop on Deep Learning for Speech Recognition and Related Applications. December, 2009, Whistler, BC, Canada.
• Ordinal Boltzmann Machines for Collaborative Filtering. Tran The Truyen, Dinh Q. Phung and Svetha Venkatesh. In Proc. of 25th Conference on Uncertainty in Artificial Intelligence, June, 2009, Montreal, Canada. Runner-up for the best paper award.

2008

• Hierarchical Semi-Markov Conditional Random Fields for Recursive Sequential Data . Tran The Truyen, Dinh Q. Phung, Hung H. Bui, and Svetha Venkatesh. In Proc. of 21st Annual Conference on Neural Information Processing Systems, Dec 2008, Vancouver, Canada. [See technical report and thesis for more details and extensions.]
• Constrained Sequence Classification for Lexical Disambiguation . Tran The Truyen, Dinh Q. Phung and Svetha Venkatesh. In Proc. of 10th Pacific Rim International Conference on Artificial Intelligence (PRICAI-08), 15-19 Dec 2008, Hanoi, Vietnam.
• Learning Discriminative Sequence Models from Partially Labelled Data for Activity Recognition . Tran The Truyen, Hung Hai Bui, Dinh Q. Phung and Svetha Venkatesh. In Proc. of 10th Pacific Rim International Conference on Artificial Intelligence (PRICAI-08), 15-19 Dec 2008, Hanoi, Vietnam.

2005-2007

• Preference Networks: probabilistic models for recommendation systems , Tran The Truyen, Dinh Q. Phung and Svetha Venkatesh, In Proc. of 6th Australasian Data Mining Conference: AusDM 2007, 3-4 Dec, Gold Coast, Australia. 

• AdaBoost.MRF: Boosted Markov random forests and application to multilevel activity recognition , Tran The Truyen, Dinh Quoc Phung, Hung Hai Bui, and Svetha Venkatesh. In Proc. of  IEEE Conference on Computer Vision and Pattern Recognition, volume Volume 2, pages 1686-1693, New York, USA, June 2006.

• Boosted Markov networks for activity recognition , Tran The Truyen, Hung Hai Bui and Svetha Venkatesh, In Proc. of International Conference on Intelligent Sensors, Sensor Networks and Information Processing (ISSNIP2005), 5-8 Dec, Melbourne, Australia.

Unpublished: Technical reports, Tutorials and Notes