1 code implementation • 12 Apr 2024 • Emadeldeen Eldele, Mohamed Ragab, Zhenghua Chen, Min Wu, XiaoLi Li
Time series data, characterized by its intrinsic long and short-range dependencies, poses a unique challenge across analytical applications.
no code implementations • 3 Apr 2024 • Weichao Lan, Yiu-ming Cheung, Qing Xu, Buhua Liu, Zhikai Hu, Mengke Li, Zhenghua Chen
In addition to the supervision of ground truth, the vanilla KD method regards the predictions of the teacher as soft labels to supervise the training of the student model.
no code implementations • 6 Mar 2024 • Yucheng Wang, Ruibing Jin, Min Wu, XiaoLi Li, Lihua Xie, Zhenghua Chen
To capture these dependencies, Graph Neural Networks (GNNs) have emerged as powerful tools, yet their effectiveness is restricted by the quality of graph construction from MTS data.
1 code implementation • 4 Mar 2024 • Cunyi Yin, Xiren Miao, Jing Chen, Hao Jiang, Jianfei Yang, Yunjiao Zhou, Min Wu, Zhenghua Chen
WiFi-based human pose estimation is a suitable method for monitoring power operations due to its low cost, device-free, and robustness to various illumination conditions. In this paper, a novel Channel State Information (CSI)-based pose estimation framework, namely PowerSkel, is developed to address these challenges.
no code implementations • 17 Nov 2023 • Yucheng Wang, Yuecong Xu, Jianfei Yang, Min Wu, XiaoLi Li, Lihua Xie, Zhenghua Chen
In this paper, we propose SEnsor Alignment (SEA) for MTS-UDA, aiming to reduce domain discrepancy at both the local and global sensor levels.
no code implementations • 22 Oct 2023 • Hongxiang Gao, Xiangyao Wang, Zhenghua Chen, Min Wu, Zhipeng Cai, Lulu Zhao, Jianqing Li, Chengyu Liu
To address these challenges, this study introduces the distribution-based uncertainty method to represent spatial dependencies and temporal-spectral relativeness in EEG signals based on Graph Convolutional Network (GCN) architecture that adaptively assigns weights to functional aggregate node features, enabling effective long-path capturing while mitigating over-smoothing phenomena.
1 code implementation • 11 Sep 2023 • Yucheng Wang, Yuecong Xu, Jianfei Yang, Min Wu, XiaoLi Li, Lihua Xie, Zhenghua Chen
As MTS data typically originate from multiple sensors, ensuring spatial consistency becomes essential for the overall performance of contrastive learning on MTS data.
1 code implementation • 11 Sep 2023 • Yucheng Wang, Yuecong Xu, Jianfei Yang, Min Wu, XiaoLi Li, Lihua Xie, Zhenghua Chen
For graph construction, we design a decay graph to connect sensors across all timestamps based on their temporal distances, enabling us to fully model the ST dependencies by considering the correlations between DEDT.
no code implementations • 18 Aug 2023 • Ruibing Jin, Guosheng Lin, Min Wu, Jie Lin, Zhengguo Li, XiaoLi Li, Zhenghua Chen
To address this issue, we propose an unlimited knowledge distillation (UKD) in this paper.
no code implementations • 30 Jul 2023 • Chenxi Huang, Chaoyang Jiang, Zhenghua Chen
Specifically, we employ local differential privacy to extend the privacy protection trust boundary to the clients.
1 code implementation • 14 Jul 2023 • Mohamed Ragab, Emadeldeen Eldele, Min Wu, Chuan-Sheng Foo, XiaoLi Li, Zhenghua Chen
The existing SFDA methods that are mainly designed for visual applications may fail to handle the temporal dynamics in time series, leading to impaired adaptation performance.
1 code implementation • 7 Jul 2023 • Qing Xu, Min Wu, XiaoLi Li, Kezhi Mao, Zhenghua Chen
More specifically, a feature-domain discriminator is employed to align teacher's and student's representations for universal knowledge transfer.
no code implementations • 10 Apr 2023 • Hongxiang Gao, Xingyao Wang, Zhenghua Chen, Min Wu, Jianqing Li, Chengyu Liu
From the perspective of intelligent wearable applications, the possibility of a comprehensive ECG interpretation algorithm based on single-lead ECGs is also confirmed.
no code implementations • ICCV 2023 • Yuecong Xu, Jianfei Yang, Yunjiao Zhou, Zhenghua Chen, Min Wu, XiaoLi Li
We thus consider a more realistic \textit{Few-Shot Video-based Domain Adaptation} (FSVDA) scenario where we adapt video models with only a few target video samples.
1 code implementation • 27 Feb 2023 • Jianan Zhou, Yaoxin Wu, Zhiguang Cao, Wen Song, Jie Zhang, Zhenghua Chen
Dispatching vehicle fleets to serve flights is a key task in airport ground handling (AGH).
no code implementations • 13 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.
1 code implementation • 3 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.
no code implementations • 17 Nov 2022 • Yuecong Xu, Haozhi Cao, Zhenghua Chen, XiaoLi Li, Lihua Xie, Jianfei Yang
To tackle performance degradation and address concerns in high video annotation cost uniformly, the video unsupervised domain adaptation (VUDA) is introduced to adapt video models from the labeled source domain to the unlabeled target domain by alleviating video domain shift, improving the generalizability and portability of video models.
1 code implementation • 10 Oct 2022 • Emadeldeen Eldele, Mohamed Ragab, Zhenghua Chen, Min Wu, Chee-Keong Kwoh, XiaoLi Li
The past few years have witnessed a remarkable advance in deep learning for EEG-based sleep stage classification (SSC).
2 code implementations • 13 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.
no code implementations • 10 Aug 2022 • Yuecong Xu, Jianfei Yang, Haozhi Cao, Min Wu, XiaoLi Li, Lihua Xie, Zhenghua Chen
To enable video models to be applied seamlessly across video tasks in different environments, various Video Unsupervised Domain Adaptation (VUDA) methods have been proposed to improve the robustness and transferability of video models.
no code implementations • 8 May 2022 • Zhenghua Chen, Min Wu, Alvin Chan, XiaoLi Li, Yew-Soon Ong
We believe that this technical review can help to promote a sustainable development of AI R&D activities for the research community.
1 code implementation • 15 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.
1 code implementation • 9 Mar 2022 • Yuecong Xu, Jianfei Yang, Haozhi Cao, Keyu Wu, Wu Min, Zhenghua Chen
Video-based Unsupervised Domain Adaptation (VUDA) methods improve the robustness of video models, enabling them to be applied to action recognition tasks across different environments.
no code implementations • 19 Feb 2022 • Yuecong Xu, Jianfei Yang, Haozhi Cao, Jianxiong Yin, Zhenghua Chen, XiaoLi Li, Zhengguo Li, Qianwen Xu
While action recognition (AR) has gained large improvements with the introduction of large-scale video datasets and the development of deep neural networks, AR models robust to challenging environments in real-world scenarios are still under-explored.
1 code implementation • 29 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.
2 code implementations • NeurIPS 2021 • Yining Ma, Jingwen Li, Zhiguang Cao, Wen Song, Le Zhang, Zhenghua Chen, Jing Tang
Moreover, the positional features are embedded through a novel cyclic positional encoding (CPE) method to allow Transformer to effectively capture the circularity and symmetry of VRP solutions (i. e., cyclic sequences).
no code implementations • 29 Sep 2021 • Mohamed Ragab, Emadeldeen Eldele, Wee Ling Tan, Chuan-Sheng Foo, Zhenghua Chen, Min Wu, Chee Kwoh, XiaoLi Li
Our evaluation includes adaptations of state-of-the-art visual domain adaptation methods to time series data in addition to recent methods specifically developed for time series data.
no code implementations • 21 Sep 2021 • Yuecong Xu, Jianfei Yang, Haozhi Cao, Keyu Wu, Min Wu, Rui Zhao, Zhenghua Chen
Multi-Source Domain Adaptation (MSDA) is a more practical domain adaptation scenario in real-world scenarios.
no code implementations • 20 Jul 2021 • Xingxing Yang, Jie Chen, Zaifeng Yang, Zhenghua Chen
Finally, a Fusion Attention Block (FAB) is proposed to adaptively fuse the features from the two branches and generate an optimized colorization result.
no code implementations • ICCV 2021 • Yuecong Xu, Jianfei Yang, Haozhi Cao, Qi Li, Kezhi Mao, Zhenghua Chen
For videos, such negative transfer could be triggered by both spatial and temporal features, which leads to a more challenging Partial Video Domain Adaptation (PVDA) problem.
1 code implementation • 9 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.
1 code implementation • 26 Jun 2021 • Emadeldeen Eldele, Mohamed Ragab, Zhenghua Chen, Min Wu, Chee Keong Kwoh, XiaoLi Li, Cuntai Guan
In this paper, we propose an unsupervised Time-Series representation learning framework via Temporal and Contextual Contrasting (TS-TCC), to learn time-series representation from unlabeled data.
Ranked #1 on Recognizing And Localizing Human Actions on HAR
Automatic Sleep Stage Classification Contrastive Learning +9
1 code implementation • 28 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.
Ranked #1 on Automatic Sleep Stage Classification on Sleep-EDF
no code implementations • 18 Jan 2021 • Rooholla Khorrambakht, Chris Xiaoxuan Lu, Hamed Damirchi, Zhenghua Chen, Zhengguo Li
Inertial Measurement Units (IMUs) are interceptive modalities that provide ego-motion measurements independent of the environmental factors.
no code implementations • 20 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.
1 code implementation • 21 Jan 2019 • Haofan Wang, Zhenghua Chen, Yi Zhou
In this paper, to do the estimation without facial landmarks, we combine the coarse and fine regression output together for a deep network.
Ranked #3 on Head Pose Estimation on AFLW
1 code implementation • 16 Dec 2016 • Rui Zhao, Ruqiang Yan, Zhenghua Chen, Kezhi Mao, Peng Wang, Robert X. Gao
Since 2006, deep learning (DL) has become a rapidly growing research direction, redefining state-of-the-art performances in a wide range of areas such as object recognition, image segmentation, speech recognition and machine translation.