Search Results for author: Kien A. Hua

Found 11 papers, 1 papers with code

Improving Online Forums Summarization via Hierarchical Unified Deep Neural Network

no code implementations25 Mar 2021 Sansiri Tarnpradab, Fereshteh Jafariakinabad, Kien A. Hua

In this scheme, Bi-LSTM derives a representation that comprises information of the whole sentence and whole thread; whereas, CNN captures most informative features with respect to context from sentence and thread.

A Self-supervised Representation Learning of Sentence Structure for Authorship Attribution

1 code implementation14 Oct 2020 Fereshteh Jafariakinabad, Kien A. Hua

Due to the n-to-1 mapping of words to their structural labels, each word will be embedded into a vector representation which mainly carries structural information.

Word Embeddings

Style-aware Neural Model with Application in Authorship Attribution

no code implementations12 Sep 2019 Fereshteh Jafariakinabad, Kien A. Hua

Writing style is a combination of consistent decisions associated with a specific author at different levels of language production, including lexical, syntactic, and structural.

Differential Recurrent Neural Network and its Application for Human Activity Recognition

no code implementations9 May 2019 Naifan Zhuang, Guo-Jun Qi, The Duc Kieu, Kien A. Hua

The Long Short-Term Memory (LSTM) recurrent neural network is capable of processing complex sequential information since it utilizes special gating schemes for learning representations from long input sequences.

Activity Recognition Time Series

Syntactic Recurrent Neural Network for Authorship Attribution

no code implementations26 Feb 2019 Fereshteh Jafariakinabad, Sansiri Tarnpradab, Kien A. Hua

In this paper, we introduce a syntactic recurrent neural network to encode the syntactic patterns of a document in a hierarchical structure.

Hierarchical structure Text Classification

Deep Segment Hash Learning for Music Generation

no code implementations30 May 2018 Kevin Joslyn, Naifan Zhuang, Kien A. Hua

Music generation research has grown in popularity over the past decade, thanks to the deep learning revolution that has redefined the landscape of artificial intelligence.

Music Generation

Deep Differential Recurrent Neural Networks

no code implementations11 Apr 2018 Naifan Zhuang, The Duc Kieu, Guo-Jun Qi, Kien A. Hua

The proposed model progressively builds up the ability of the LSTM gates to detect salient dynamical patterns in deeper stacked layers modeling higher orders of DoS, and thus the proposed LSTM model is termed deep differential Recurrent Neural Network (d2RNN).

First-Take-All: Temporal Order-Preserving Hashing for 3D Action Videos

no code implementations6 Jun 2015 Jun Ye, Hao Hu, Kai Li, Guo-Jun Qi, Kien A. Hua

With the prevalence of the commodity depth cameras, the new paradigm of user interfaces based on 3D motion capturing and recognition have dramatically changed the way of interactions between human and computers.

3D Action Recognition

Rank Subspace Learning for Compact Hash Codes

no code implementations19 Mar 2015 Kai Li, Guo-Jun Qi, Jun Ye, Kien A. Hua

In this work, we propose a novel hash learning framework that encodes feature's rank orders instead of numeric values in a number of optimal low-dimensional ranking subspaces.

Cannot find the paper you are looking for? You can Submit a new open access paper.