Jiehui Huang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Jiehui Huang has a total of 53 co-authors. Here are the top co-authors by number of shared publications:
- Calvin Yu-Chian Chen
AI for Science (AI4S)-Preferred Program, Peking University Shenzhen Graduate School, Shenzhen, China
4 shared publications - Chunquan Li
School of Information Engineering, Nanchang University, Nanchang, China
3 shared publications - Peter Xiaoping Liu
Department of Systems and Computer Engineering, Carleton University, Ottawa, ON, Canada
3 shared publications - Xiaodan Liang
Shenzhen Campus of Sun Yat-sen University
3 shared publications - Hanhui Li
Shenzhen Campus of Sun Yat-sen University, Shenzhen, China
2 shared publications Jun Zhou
2 shared publications
Latest Publications
- Open Access
- 28 August 2026
- Published by American Association for the Advancement of Science (AAAS) in Science Advances
- Vol. 12 (35)
scProtoTransformer: Scalable reference mapping across molecules, cells, and donors
The rapid accumulation of single-cell data has made it possible to comprehensively characterize biological systems at molecular, cellular, and donor levels. However, scalable reference mapping across different resolutions remains a major challenge in current research. Here, we propose scProtoTransformer, a prototype-based Transformer architecture designed to achieve scalable reference mapping across molecular, cell, and donor levels. scProtoTransformer introduces a knowledge-guided prototype tokenizer that projects gene expression into biologically interpretable pathway prototypes, effectively reducing numerical batch effects while preserving biological semantic patterns. Furthermore, by leveraging knowledge distilled from the foundation model and a dynamic supervised fine-tuning strategy, scProtoTransformer achieves robust biological representations with reduced pretraining requirements. Benchmark experiments across molecular, cell, and donor-level reference mapping demonstrate that scProtoTransformer delivers competitive or even superior performance compared with state-of-the-art approaches while providing interpretability through biological prototypes. Together, these results establish scProtoTransformer as a unified framework for scalable reference mapping, laying the foundation for systematic understanding from genes to individuals.
- 28 August 2026
- Published by American Association for the Advancement of Science (AAAS) in Science Advances
- Vol. 12 (35)
Open AccessscProtoTransformer: Scalable reference mapping across molecules, cells, and donors
The rapid accumulation of single-cell data has made it possible to comprehensively characterize biological systems at molecular, cellular, and donor levels. However, scalable reference mapping across different resolutions remains a major challenge in current research. Here, we propose scProtoTransformer, a prototype-based Transformer architecture designed to achieve scalable reference mapping across molecular, cell, and donor levels. scProtoTransformer introduces a knowledge-guided prototype tokenizer that projects gene expression into biologically interpretable pathway prototypes, effectively reducing numerical batch effects while preserving biological semantic patterns. Furthermore, by leveraging knowledge distilled from the foundation model and a dynamic supervised fine-tuning strategy, scProtoTransformer achieves robust biological representations with reduced pretraining requirements. Benchmark experiments across molecular, cell, and donor-level reference mapping demonstrate that scProtoTransformer delivers competitive or even superior performance compared with state-of-the-art approaches while providing interpretability through biological prototypes. Together, these results establish scProtoTransformer as a unified framework for scalable reference mapping, laying the foundation for systematic understanding from genes to individuals.
- Top Cited Papers
- 12 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 48 (5) , 5639-5654
ConsistentID: Portrait Generation With Multimodal Fine-Grained Identity Preserving
Diffusion-based technologies have made significant strides, particularly in personalized and customized facial generation. However, existing methods struggle to achieve high-fidelity and detailed identity (ID) consistency. This is mainly due to two challenges: insufficient fine-grained control over specific facial areas and the absence of a comprehensive strategy for ID preservation that accounts for both intricate facial details and the overall facial structure. To address these limitations, we introduce ConsistentID, an innovative method crafted for diverse identity-preserving portrait generation under fine-grained multimodal facial prompts, utilizing only a single reference image. ConsistentID comprises two core components: a multimodal facial prompt generator and an ID-preservation network. The facial prompt generator combines localized facial features, facial feature descriptions, and overall facial descriptions to enhance the precision of facial detail reconstruction. The ID-preservation network, optimized with a facial attention localization strategy, ensures consistent identity preservation across facial regions. Together, these components leverage fine-grained multimodal identity information to improve identity preservation accuracy significantly. To drive ConsistentID’s training, we propose a fine-grained portrait dataset, FGID, with over 500,000 facial images, offering greater diversity and comprehensiveness than existing public facial datasets. Experimental results substantiate that our ConsistentID achieves exceptional precision and diversity in personalized facial generation, surpassing existing methods in the MyStyle dataset. In addition, although ConsistentID introduces more multimodal ID information, it still maintains rapid inference speed during the generation process.
- 12 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 48 (5) , 5639-5654
Top Cited PapersConsistentID: Portrait Generation With Multimodal Fine-Grained Identity Preserving
Diffusion-based technologies have made significant strides, particularly in personalized and customized facial generation. However, existing methods struggle to achieve high-fidelity and detailed identity (ID) consistency. This is mainly due to two challenges: insufficient fine-grained control over specific facial areas and the absence of a comprehensive strategy for ID preservation that accounts for both intricate facial details and the overall facial structure. To address these limitations, we introduce ConsistentID, an innovative method crafted for diverse identity-preserving portrait generation under fine-grained multimodal facial prompts, utilizing only a single reference image. ConsistentID comprises two core components: a multimodal facial prompt generator and an ID-preservation network. The facial prompt generator combines localized facial features, facial feature descriptions, and overall facial descriptions to enhance the precision of facial detail reconstruction. The ID-preservation network, optimized with a facial attention localization strategy, ensures consistent identity preservation across facial regions. Together, these components leverage fine-grained multimodal identity information to improve identity preservation accuracy significantly. To drive ConsistentID’s training, we propose a fine-grained portrait dataset, FGID, with over 500,000 facial images, offering greater diversity and comprehensiveness than existing public facial datasets. Experimental results substantiate that our ConsistentID achieves exceptional precision and diversity in personalized facial generation, surpassing existing methods in the MyStyle dataset. In addition, although ConsistentID introduces more multimodal ID information, it still maintains rapid inference speed during the generation process.
- Open Access
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 9529-9538
LaVieID: Local Autoregressive Diffusion Transformers for Identity-Preserving Video Creation
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 9529-9538
Open AccessLaVieID: Local Autoregressive Diffusion Transformers for Identity-Preserving Video Creation
- 21 February 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 74 (00189456) , 1-11
A Novel End-to-End 3-D Residual and Attention Enhancement Joint Few-Shot Learning Model for Huntington Clinical Assessment
Sign assessment in Huntingtons disease (HD) holds significant importance for its treatment. However, most of the existing methods to assess motor signs have shortcomings. Newer ones are in development but may be expensive, and few studies have employed end-to-end video-based motor assessments. To fill this research gap, we developed a few-shot learning model based on a 3D residual and attention enhancement joint learning approach. We first collected video data from 48 HD patients and enhanced the key data. We then designed a 3D convolutional module based on channel-spatial attention to initially extract data features. After that, an excitation-based 3D residual convolution module was designed for feature learning. Finally, we used a fully connected layer based on channel-spatial attention to complete feature compression and obtain the assessment results. Our results show that the classification accuracy and recall of our model achieve state-of-the-art performance. The proposed lightweight HD disease motor assessment model is an improvement over other previous methods. Further developments of the methods are expected to provide a suitable baseline and follow-up assessment tool for future HD video-based studies. Furthermore, our proposed solution can be implemented with consumer-grade cameras, holding considerable potential for extensive implementation in HD telemedicine. The source code can be found at https://github.com/JackAILab/RAJNet.
- 21 February 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 74 (00189456) , 1-11
A Novel End-to-End 3-D Residual and Attention Enhancement Joint Few-Shot Learning Model for Huntington Clinical Assessment
Sign assessment in Huntingtons disease (HD) holds significant importance for its treatment. However, most of the existing methods to assess motor signs have shortcomings. Newer ones are in development but may be expensive, and few studies have employed end-to-end video-based motor assessments. To fill this research gap, we developed a few-shot learning model based on a 3D residual and attention enhancement joint learning approach. We first collected video data from 48 HD patients and enhanced the key data. We then designed a 3D convolutional module based on channel-spatial attention to initially extract data features. After that, an excitation-based 3D residual convolution module was designed for feature learning. Finally, we used a fully connected layer based on channel-spatial attention to complete feature compression and obtain the assessment results. Our results show that the classification accuracy and recall of our model achieve state-of-the-art performance. The proposed lightweight HD disease motor assessment model is an improvement over other previous methods. Further developments of the methods are expected to provide a suitable baseline and follow-up assessment tool for future HD video-based studies. Furthermore, our proposed solution can be implemented with consumer-grade cameras, holding considerable potential for extensive implementation in HD telemedicine. The source code can be found at https://github.com/JackAILab/RAJNet.
- Top Cited Papers
- 28 December 2023
- Published by Elsevier in Knowledge-Based Systems
- Vol. 285
TMBL: Transformer-based multimodal binding learning model for multimodal sentiment analysis
- 28 December 2023
- Published by Elsevier in Knowledge-Based Systems
- Vol. 285
Top Cited PapersTMBL: Transformer-based multimodal binding learning model for multimodal sentiment analysis
- 21 November 2023
- Published by Elsevier in Neurocomputing
- Vol. 568
Progressive network based on detail scaling and texture extraction: A more general framework for image deraining
- 21 November 2023
- Published by Elsevier in Neurocomputing
- Vol. 568
Progressive network based on detail scaling and texture extraction: A more general framework for image deraining
- Open Access
- 22 July 2022
- Published by MDPI AG in Sustainability
- Vol. 14 (15) , 9021
A Hybrid Generative Adversarial Network Model for Ultra Short-Term Wind Speed Prediction
To improve the accuracy of ultra-short-term wind speed prediction, a hybrid generative adversarial network model (HGANN) is proposed in this paper. Firstly, to reduce the noise of the wind sequence, the raw wind data are decomposed using complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN). Then the decomposed modalities are entered into the HGANN network for prediction. HGANN is a continuous game between the generator and the discriminator, which in turn allows the generator to learn the distribution of the wind data and make predictions about it. Notably, we developed the optimized broad learning system (OBLS) as a generator for the HGANN network, which can improve the generalization ability and error convergence of HGANN. In addition, improved particle swarm optimization (IPSO) was used to optimize the hyperparameters of OBLS. To validate the performance of the HGANN model, experiments were conducted using wind sequences from different regions and at different times. The experimental results show that our model outperforms other cutting-edge benchmark models in single-step and multi-step forecasts. This demonstrates not only the accuracy and robustness of the proposed model but also the applicability of our model to more general environments for wind speed prediction.
- 22 July 2022
- Published by MDPI AG in Sustainability
- Vol. 14 (15) , 9021
Open AccessA Hybrid Generative Adversarial Network Model for Ultra Short-Term Wind Speed Prediction
To improve the accuracy of ultra-short-term wind speed prediction, a hybrid generative adversarial network model (HGANN) is proposed in this paper. Firstly, to reduce the noise of the wind sequence, the raw wind data are decomposed using complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN). Then the decomposed modalities are entered into the HGANN network for prediction. HGANN is a continuous game between the generator and the discriminator, which in turn allows the generator to learn the distribution of the wind data and make predictions about it. Notably, we developed the optimized broad learning system (OBLS) as a generator for the HGANN network, which can improve the generalization ability and error convergence of HGANN. In addition, improved particle swarm optimization (IPSO) was used to optimize the hyperparameters of OBLS. To validate the performance of the HGANN model, experiments were conducted using wind sequences from different regions and at different times. The experimental results show that our model outperforms other cutting-edge benchmark models in single-step and multi-step forecasts. This demonstrates not only the accuracy and robustness of the proposed model but also the applicability of our model to more general environments for wind speed prediction.
- Open Access
- 25 May 2022
- Published by MDPI AG in Mathematics
- Vol. 10 (11) , 1824
A Multi-View Ensemble Width-Depth Neural Network for Short-Term Wind Power Forecasting
Short-term wind power forecasting (SWPF) is essential for managing wind power systems management. However, most existing forecasting methods fail to fully consider how to rationally integrate multi-view learning technologies with attention mechanisms. In this case, some potential features cannot be fully extracted, degenerating the predictive accuracy and robustness in SWPF. To solve this problem, this paper proposes a multi-view ensemble width-depth neural network (MVEW-DNN) for SWPF. Specifically, MVEW-DNN consists of local and global view learning subnetworks, which can effectively achieve more potential global and local view features of the original wind power data. In MVEW-DNN, the local view learning subnetwork is developed by introducing the deep belief network (DBN) model, which can efficiently extract the local view features. On the other hand, by introducing the attention mechanism, a new deep encoder board learning system (deBLS) is developed as the global view learning subnetwork, which provides more comprehensive global information. Therefore, by rationally learning the effective local and global view features, MVEW-DNN can achieve competitive predictive performance in SWPF. MVEW-DNN is compared with the state-of-the-art models in SWPF. The experiment results indicate that MVEW-DNN can provide competitive predictive accuracy and robustness.
- 25 May 2022
- Published by MDPI AG in Mathematics
- Vol. 10 (11) , 1824
Open AccessA Multi-View Ensemble Width-Depth Neural Network for Short-Term Wind Power Forecasting
Short-term wind power forecasting (SWPF) is essential for managing wind power systems management. However, most existing forecasting methods fail to fully consider how to rationally integrate multi-view learning technologies with attention mechanisms. In this case, some potential features cannot be fully extracted, degenerating the predictive accuracy and robustness in SWPF. To solve this problem, this paper proposes a multi-view ensemble width-depth neural network (MVEW-DNN) for SWPF. Specifically, MVEW-DNN consists of local and global view learning subnetworks, which can effectively achieve more potential global and local view features of the original wind power data. In MVEW-DNN, the local view learning subnetwork is developed by introducing the deep belief network (DBN) model, which can efficiently extract the local view features. On the other hand, by introducing the attention mechanism, a new deep encoder board learning system (deBLS) is developed as the global view learning subnetwork, which provides more comprehensive global information. Therefore, by rationally learning the effective local and global view features, MVEW-DNN can achieve competitive predictive performance in SWPF. MVEW-DNN is compared with the state-of-the-art models in SWPF. The experiment results indicate that MVEW-DNN can provide competitive predictive accuracy and robustness.
- Open Access
- 16 October 2021
- Published by Institution of Engineering and Technology (IET) in IET Generation, Transmission & Distribution
- Vol. 15 (24) , 3459-3473
A decomposition‐based multi‐time dimension long short‐term memory model for short‐term electric load forecasting
Short‐term load forecasting is essential to power systems management. However, most existing forecasting methods fail to fully consider how to rationally integrate the intrinsic time‐related dimensions of electric load data and the decomposition methods into machine learning models so that their prediction accuracy and robustness still have much room for improvement. To solve this problem, this paper proposes a decomposition‐based multi‐time dimension long short‐term memory (DB‐MTD‐LSTM) model for short‐term electric load forecasting (STELF). In DB‐MTD‐LSTM, empirical mode decomposition with adaptive noise (CEEMDAN) is first introduced to smooth non‐linear non‐stationary electric load data and constrain the modal aliasing or noise of decomposed electric load data in the traditional decomposed method. A joint relevant time dimensions method (JRTDM) is then developed using autocorrelation analysis to rationally extract the temporal characteristics of decomposed data in multiple time dimensions. An improved LSTM called MTD‐LSTM is developed by combining JRTDM with LSTM, which can effectively apply multi‐dimensional time characteristics of the decomposed load to improve the predictive accuracy and robustness. Several datasets from Australia and China are performed to check the predictive performance of DB‐MTD‐LSTM. Experimental results verify that DB‐MTD‐LSTM has better predictive accuracy and satisfactory robustness compared with state‐of‐the‐art and conventional predictive models.
- 16 October 2021
- Published by Institution of Engineering and Technology (IET) in IET Generation, Transmission & Distribution
- Vol. 15 (24) , 3459-3473
Open AccessA decomposition‐based multi‐time dimension long short‐term memory model for short‐term electric load forecasting
Short‐term load forecasting is essential to power systems management. However, most existing forecasting methods fail to fully consider how to rationally integrate the intrinsic time‐related dimensions of electric load data and the decomposition methods into machine learning models so that their prediction accuracy and robustness still have much room for improvement. To solve this problem, this paper proposes a decomposition‐based multi‐time dimension long short‐term memory (DB‐MTD‐LSTM) model for short‐term electric load forecasting (STELF). In DB‐MTD‐LSTM, empirical mode decomposition with adaptive noise (CEEMDAN) is first introduced to smooth non‐linear non‐stationary electric load data and constrain the modal aliasing or noise of decomposed electric load data in the traditional decomposed method. A joint relevant time dimensions method (JRTDM) is then developed using autocorrelation analysis to rationally extract the temporal characteristics of decomposed data in multiple time dimensions. An improved LSTM called MTD‐LSTM is developed by combining JRTDM with LSTM, which can effectively apply multi‐dimensional time characteristics of the decomposed load to improve the predictive accuracy and robustness. Several datasets from Australia and China are performed to check the predictive performance of DB‐MTD‐LSTM. Experimental results verify that DB‐MTD‐LSTM has better predictive accuracy and satisfactory robustness compared with state‐of‐the‐art and conventional predictive models.