Search Results for author: Chee-Keong Kwoh

Found 16 papers, 8 papers with code

Dual Stage Stylization Modulation for Domain Generalized Semantic Segmentation

no code implementations18 Apr 2023 Gabriel Tjio, Ping Liu, Chee-Keong Kwoh, Joey Tianyi Zhou

To tackle this challenge, we introduce a dual-stage Feature Transform (dFT) layer within the Adversarial Semantic Hallucination+ (ASH+) framework.

Domain Generalization Hallucination +1

Label-efficient Time Series Representation Learning: A Review

no code implementations13 Feb 2023 Emadeldeen Eldele, Mohamed Ragab, Zhenghua Chen, Min Wu, Chee-Keong Kwoh, XiaoLi Li

The scarcity of labeled data is one of the main challenges of applying deep learning models on time series data in the real world.

Representation Learning Self-Supervised Learning +3

Contrastive Domain Adaptation for Time-Series via Temporal Mixup

1 code implementation3 Dec 2022 Emadeldeen Eldele, Mohamed Ragab, Zhenghua Chen, Min Wu, Chee-Keong Kwoh, XiaoLi Li

Specifically, we propose a novel temporal mixup strategy to generate two intermediate augmented views for the source and target domains.

Contrastive Learning Time Series +2

Self-supervised Contrastive Representation Learning for Semi-supervised Time-Series Classification

2 code implementations13 Aug 2022 Emadeldeen Eldele, Mohamed Ragab, Zhenghua Chen, Min Wu, Chee-Keong Kwoh, XiaoLi Li, Cuntai Guan

Specifically, we propose time-series specific weak and strong augmentations and use their views to learn robust temporal relations in the proposed temporal contrasting module, besides learning discriminative representations by our proposed contextual contrasting module.

Contrastive Learning Data Augmentation +5

ADATIME: A Benchmarking Suite for Domain Adaptation on Time Series Data

1 code implementation15 Mar 2022 Mohamed Ragab, Emadeldeen Eldele, Wee Ling Tan, Chuan-Sheng Foo, Zhenghua Chen, Min Wu, Chee-Keong Kwoh, XiaoLi Li

Our evaluation includes adapting state-of-the-art visual domain adaptation methods to time series data as well as the recent methods specifically developed for time series data.

Benchmarking Time Series +2

Attention over Self-attention:Intention-aware Re-ranking with Dynamic Transformer Encoders for Recommendation

no code implementations14 Jan 2022 Zhuoyi Lin, Sheng Zang, Rundong Wang, Zhu Sun, J. Senthilnath, Chi Xu, Chee-Keong Kwoh

We then introduce a dynamic transformer encoder (DTE) to capture user-specific inter-item relationships among item candidates by seamlessly accommodating the learned latent user intentions via IDM.

Re-Ranking

Self-supervised Autoregressive Domain Adaptation for Time Series Data

1 code implementation29 Nov 2021 Mohamed Ragab, Emadeldeen Eldele, Zhenghua Chen, Min Wu, Chee-Keong Kwoh, XiaoLi Li

Second, we propose a novel autoregressive domain adaptation technique that incorporates temporal dependency of both source and target features during domain alignment.

Self-Supervised Learning Time Series +2

ADAST: Attentive Cross-domain EEG-based Sleep Staging Framework with Iterative Self-Training

1 code implementation9 Jul 2021 Emadeldeen Eldele, Mohamed Ragab, Zhenghua Chen, Min Wu, Chee-Keong Kwoh, XiaoLi Li, Cuntai Guan

Second, we design an iterative self-training strategy to improve the classification performance on the target domain via target domain pseudo labels.

Automatic Sleep Stage Classification Domain Adaptation +2

An Attention-Based Deep Learning Approach for Sleep Stage Classification With Single-Channel EEG

1 code implementation28 Apr 2021 Emadeldeen Eldele, Zhenghua Chen, Chengyu Liu, Min Wu, Chee-Keong Kwoh, XiaoLi Li, Cuntai Guan

The MRCNN can extract low and high frequency features and the AFR is able to improve the quality of the extracted features by modeling the inter-dependencies between the features.

Automatic Sleep Stage Classification EEG +2

GLIMG: Global and Local Item Graphs for Top-N Recommender Systems

no code implementations28 Jul 2020 Zhuoyi Lin, Lei Feng, Rui Yin, Chi Xu, Chee-Keong Kwoh

We argue that recommendation on global and local graphs outperforms that on a single global graph or multiple local graphs.

Recommendation Systems

Attention Sequence to Sequence Model for Machine Remaining Useful Life Prediction

no code implementations20 Jul 2020 Mohamed Ragab, Zhenghua Chen, Min Wu, Chee-Keong Kwoh, Ruqiang Yan, Xiao-Li Li

Accurate estimation of remaining useful life (RUL) of industrial equipment can enable advanced maintenance schedules, increase equipment availability and reduce operational costs.

Enhanced Ensemble Clustering via Fast Propagation of Cluster-wise Similarities

no code implementations30 Oct 2018 Dong Huang, Chang-Dong Wang, Hongxing Peng, Jian-Huang Lai, Chee-Keong Kwoh

Upon the constructed graph, a transition probability matrix is defined, based on which the random walk process is conducted to propagate the graph structural information.

Clustering

Toward Multidiversified Ensemble Clustering of High-Dimensional Data: From Subspaces to Metrics and Beyond

1 code implementation9 Oct 2017 Dong Huang, Chang-Dong Wang, Jian-Huang Lai, Chee-Keong Kwoh

The rapid emergence of high-dimensional data in various areas has brought new challenges to current ensemble clustering research.

Clustering

Classification and its applications for drug-target interaction identification

no code implementations16 Feb 2015 Jian-Ping Mei, Chee-Keong Kwoh, Peng Yang, Xiao-Li Li

Classification is one of the most popular and widely used supervised learning tasks, which categorizes objects into predefined classes based on known knowledge.

Classification Clustering +2

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