Labeled Random Finite Sets and the Bayes Multi-Target Tracking Filter
- B. Vo, B. Vo, Dinh Q. Phung
- Computer ScienceIEEE Transactions on Signal Processing
- 9 December 2013
The present paper details efficient implementations of the δ-GLMB multi-target tracking filter and presents inexpensive look-ahead strategies to reduce the number of computations.
A Novel Embedding Model for Knowledge Base Completion Based on Convolutional Neural Network
- D. Q. Nguyen, T. Nguyen, Dat Quoc Nguyen, Dinh Q. Phung
- Computer ScienceNorth American Chapter of the Association for…
- 6 December 2017
The model ConvKB advances state-of-the-art models by employing a convolutional neural network, so that it can capture global relationships and transitional characteristics between entities and relations in knowledge bases.
Activity recognition and abnormality detection with the switching hidden semi-Markov model
- T. Duong, H. Bui, Dinh Q. Phung, S. Venkatesh
- Computer ScienceComputer Vision and Pattern Recognition
- 20 June 2005
The switching hidden semi-markov model (S-HSMM) is introduced, a two-layered extension of thehidden semi-Markov model for the modeling task and an effective scheme to detect abnormality without the need for training on abnormal data is proposed.
Dual Discriminator Generative Adversarial Nets
- T. Nguyen, Trung Le, H. Vu, Dinh Q. Phung
- Computer ScienceNIPS
- 12 September 2017
A novel approach to tackle the problem of mode collapse encountered in generative adversarial network (GAN), which combines the Kullback-Leibler (KL) and reverse KL divergences into a unified objective function, thus it exploits the complementary statistical properties from these Divergences to effectively diversify the estimated density in capturing multi-modes.
MGAN: Training Generative Adversarial Nets with Multiple Generators
- Q. Hoang, T. Nguyen, Trung Le, Dinh Q. Phung
- Computer ScienceInternational Conference on Learning…
- 15 February 2018
A new approach to train the Generative Adversarial Nets with a mixture of generators to overcome the mode collapsing problem, and develops theoretical analysis to prove that, at the equilibrium, the Jensen-Shannon divergence (JSD) between the mixture of generator’ distributions and the empirical data distribution is minimal, whilst the JSD among generators' distributions is maximal, hence effectively avoiding the mode collapse problem.
Column Networks for Collective Classification
- Trang Pham, T. Tran, Dinh Q. Phung, S. Venkatesh
- Computer ScienceAAAI Conference on Artificial Intelligence
- 15 September 2016
Relational learning deals with data that are characterized by relational structures. An important task is collective classification, which is to jointly classify networked objects. While it holds…
Learning and detecting activities from movement trajectories using the hierarchical hidden Markov model
- N. Nguyen, Dinh Q. Phung, S. Venkatesh, H. Bui
- Computer ScienceComputer Vision and Pattern Recognition
- 20 June 2005
The experimental results in a real-world environment have confirmed the belief that directly modeling shared structures not only reduces computational cost, but also improves recognition accuracy when compared with the tree HHMM and the flat HMM.
A Capsule Network-based Embedding Model for Knowledge Graph Completion and Search Personalization
- D. Q. Nguyen, Thanh Vu, T. Nguyen, Dat Quoc Nguyen, Dinh Q. Phung
- Computer ScienceNorth American Chapter of the Association for…
- 13 August 2018
The proposed CapsE obtains better performance than previous state-of-the-art embedding models for knowledge graph completion on two benchmark datasets WN18RR and FB15k-237, and outperforms strong search personalization baselines on SEARCH17.
Advances in Knowledge Discovery and Data Mining
- Dinh Q. Phung, V. Tseng, Geoffrey I. Webb, B. Ho, Mohadeseh Ganji, Lida Rashidi
- Computer ScienceLecture Notes in Computer Science
- 2018
This paper proposes strategies for estimating performance of a classifier using as little labeling resource as possible and shows that these strategies can reduce the variance in estimation of classifier accuracy by a significant amount compared to simple random sampling.
Learning vector representation of medical objects via EMR-driven nonnegative restricted Boltzmann machines (eNRBM)
- T. Tran, T. Nguyen, Dinh Q. Phung, S. Venkatesh
- Computer ScienceJournal of Biomedical Informatics
- 1 April 2015
...
...