Shihui Xu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Shihui Xu has a total of 15 co-authors. Here are the top co-authors by number of shared publications:
- Like Wu
Waseda University
10 shared publications - Shigeru Fujimura
Waseda University
10 shared publications - Wenjie Liao
Graduate School of Information, Production and Systems, Waseda University, Fukuoka, Japan
10 shared publications - Jiro Tanaka
Waseda University
2 shared publications - Kelvin Cheng
Rakuten Mobile Inc., Tokyo, Japan
2 shared publications - Soh Masuko
Shibaura Institute of Technology, Tokyo, Japan
2 shared publications
Latest Publications
- Open Access
- 19 June 2026
- Published by Taylor & Francis in Behaviour & Information Technology
- p. 1-28
Behaviour-driven adaptive feedback in LLM-guided 3D spatial tasks: effects on trust, reflection, and task performance
- 19 June 2026
- Published by Taylor & Francis in Behaviour & Information Technology
- p. 1-28
Open AccessBehaviour-driven adaptive feedback in LLM-guided 3D spatial tasks: effects on trust, reflection, and task performance
- Open Access
- 27 February 2026
- Published by Springer Nature in The International Journal of Advanced Manufacturing Technology
- Vol. 143 (5-6) , 3413-3426
CHIPS: Human-AI collaborative prompt generation for industrial defect segmentation
- 27 February 2026
- Published by Springer Nature in The International Journal of Advanced Manufacturing Technology
- Vol. 143 (5-6) , 3413-3426
Open AccessCHIPS: Human-AI collaborative prompt generation for industrial defect segmentation
- 15 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Visualization and Computer Graphics
- Vol. 32 (3) , 2741-2757
Incorporating Drone Into Mixed Reality for Enhanced Remote Collaboration: A User Study on Inspection Task
We present a novel Mixed Reality (MR) remote collaboration system that integrates a telepresence drone to overcome viewpoint limitations in previous approaches. Current remote collaboration systems often restrict remote users to the local user’s perspective or a fixed viewpoint, which may reduce spatial awareness and collaboration effectiveness. Our proposed system enables a remote user wearing a VR headset to independently navigate the local environment through a drone while guiding a local AR headset user. The drone represents the remote user physically and virtually with an AR avatar. The system provides the remote user with a 3D reconstruction of the local environment, the local user’s avatar, and real-time drone camera video to facilitate drone operation and collaboration. A user study comparing our drone-enhanced MR system with 2D video and 360-degree video MR systems during inspection tasks revealed that the telepresence drone significantly improved collaboration efficiency and enhanced users’ social presence and spatial presence. However, the remote users perceived a higher workload. Our findings demonstrate the benefits of independent spatial navigation through drones in remote collaboration and offer insights for future drone-enhanced MR remote collaboration systems.
- 15 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Visualization and Computer Graphics
- Vol. 32 (3) , 2741-2757
Incorporating Drone Into Mixed Reality for Enhanced Remote Collaboration: A User Study on Inspection Task
We present a novel Mixed Reality (MR) remote collaboration system that integrates a telepresence drone to overcome viewpoint limitations in previous approaches. Current remote collaboration systems often restrict remote users to the local user’s perspective or a fixed viewpoint, which may reduce spatial awareness and collaboration effectiveness. Our proposed system enables a remote user wearing a VR headset to independently navigate the local environment through a drone while guiding a local AR headset user. The drone represents the remote user physically and virtually with an AR avatar. The system provides the remote user with a 3D reconstruction of the local environment, the local user’s avatar, and real-time drone camera video to facilitate drone operation and collaboration. A user study comparing our drone-enhanced MR system with 2D video and 360-degree video MR systems during inspection tasks revealed that the telepresence drone significantly improved collaboration efficiency and enhanced users’ social presence and spatial presence. However, the remote users perceived a higher workload. Our findings demonstrate the benefits of independent spatial navigation through drones in remote collaboration and offer insights for future drone-enhanced MR remote collaboration systems.
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 37 (10) , 1-15
Dual-Path Conditional Diffusion Model With Attribute Consistency for Zero-Shot Fault Diagnosis
In traditional data-driven fault diagnosis, acquiring training examples for all potential fault classes is highly challenging. Zero-shot learning (ZSL) methods based on generative adversarial networks (GANs) have shown promising results; however, these approaches suffer from training instability, mode collapse, and a lack of robustness. To overcome these limitations, this article proposes a novel dual-path conditional denoising diffusion probabilistic model with attribute consistency (DP-CDDPM-AC) for zero-shot fault diagnosis (ZSFD). Specifically, a dual-path diffusion mechanism is introduced, comprising a feature-based diffusion path and an attribute-based diffusion path. The feature-based diffusion path employs a conditional reverse denoising process to generate realistic and diverse samples for unseen fault classes. Simultaneously, the attribute-based diffusion path explicitly models the complex attribute distribution, providing robust and informative attribute representations. By leveraging intermediate noisy attribute representations from the attribute-based path, the feature-based path effectively enhances attribute consistency, robustness to noisy or ambiguous attributes, and mitigates the domain shift problem inherent in zero-shot scenarios. In addition, an attribute regressor is integrated to introduce an attribute-consistent loss, further ensuring generated features align well with their corresponding attributes. A clustered KL-guided filter and feature concatenation operation are adopted to select qualified generated features and synthesize more discriminative fault features, respectively. Extensive experiments on three fault diagnosis datasets demonstrate that the proposed DP-CDDPM-AC significantly outperforms other methods.
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 37 (10) , 1-15
Dual-Path Conditional Diffusion Model With Attribute Consistency for Zero-Shot Fault Diagnosis
In traditional data-driven fault diagnosis, acquiring training examples for all potential fault classes is highly challenging. Zero-shot learning (ZSL) methods based on generative adversarial networks (GANs) have shown promising results; however, these approaches suffer from training instability, mode collapse, and a lack of robustness. To overcome these limitations, this article proposes a novel dual-path conditional denoising diffusion probabilistic model with attribute consistency (DP-CDDPM-AC) for zero-shot fault diagnosis (ZSFD). Specifically, a dual-path diffusion mechanism is introduced, comprising a feature-based diffusion path and an attribute-based diffusion path. The feature-based diffusion path employs a conditional reverse denoising process to generate realistic and diverse samples for unseen fault classes. Simultaneously, the attribute-based diffusion path explicitly models the complex attribute distribution, providing robust and informative attribute representations. By leveraging intermediate noisy attribute representations from the attribute-based path, the feature-based path effectively enhances attribute consistency, robustness to noisy or ambiguous attributes, and mitigates the domain shift problem inherent in zero-shot scenarios. In addition, an attribute regressor is integrated to introduce an attribute-consistent loss, further ensuring generated features align well with their corresponding attributes. A clustered KL-guided filter and feature concatenation operation are adopted to select qualified generated features and synthesize more discriminative fault features, respectively. Extensive experiments on three fault diagnosis datasets demonstrate that the proposed DP-CDDPM-AC significantly outperforms other methods.
- Open Access
- 27 July 2025
- Published by Taylor & Francis in International Journal of Human–Computer Interaction
- Vol. 42 (5) , 3615-3651
Augmented Remote Assistance for Quality Inspection: A Cross-Reality Collaborative System With Virtual Replicas
- 27 July 2025
- Published by Taylor & Francis in International Journal of Human–Computer Interaction
- Vol. 42 (5) , 3615-3651
Open AccessAugmented Remote Assistance for Quality Inspection: A Cross-Reality Collaborative System With Virtual Replicas
- 13 March 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 74 (00189456) , 1-13
Cycle-Consistent Generating Network Based on Semantic Distance for Zero-Shot Fault Diagnosis
In conventional data-driven fault diagnosis scenarios, it is often challenging to acquire sufficient training instances for every potential fault category. Because many target faults cannot be collected in advance, these gaps can constrain the effectiveness of existing diagnostic models. Zero-shot learning has gained prominence as a viable solution to this problem. However, it often encounters the issue of domain shift and insufficient learning of semantic space. In this study, a novel approach named the cycle-consistent generative adversarial network with semantic distance (CycleGAN-SD) is proposed for zero-shot fault diagnosis. By defining the semantic distance between different fault classes in attribute feature space, CycleGAN-SD facilitates the transformation of fault data from seen to unseen classes. To alleviate the issue that the generated features may deviate from real faults, an attribute regressor is introduced to construct the attribute-consistent loss. Besides, this method also introduces feature concatenation to build new training data and testing data. By merging the synthesized features, a more distinctive representation is achieved, thereby enhancing subsequent fault diagnosis. To validate the effectiveness of the proposed method, three fault diagnosis scenarios were investigated. Furthermore, the experimental results demonstrate that the proposed method surpasses other state-of-the-art zero-shot fault diagnosis techniques.
- 13 March 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 74 (00189456) , 1-13
Cycle-Consistent Generating Network Based on Semantic Distance for Zero-Shot Fault Diagnosis
In conventional data-driven fault diagnosis scenarios, it is often challenging to acquire sufficient training instances for every potential fault category. Because many target faults cannot be collected in advance, these gaps can constrain the effectiveness of existing diagnostic models. Zero-shot learning has gained prominence as a viable solution to this problem. However, it often encounters the issue of domain shift and insufficient learning of semantic space. In this study, a novel approach named the cycle-consistent generative adversarial network with semantic distance (CycleGAN-SD) is proposed for zero-shot fault diagnosis. By defining the semantic distance between different fault classes in attribute feature space, CycleGAN-SD facilitates the transformation of fault data from seen to unseen classes. To alleviate the issue that the generated features may deviate from real faults, an attribute regressor is introduced to construct the attribute-consistent loss. Besides, this method also introduces feature concatenation to build new training data and testing data. By merging the synthesized features, a more distinctive representation is achieved, thereby enhancing subsequent fault diagnosis. To validate the effectiveness of the proposed method, three fault diagnosis scenarios were investigated. Furthermore, the experimental results demonstrate that the proposed method surpasses other state-of-the-art zero-shot fault diagnosis techniques.
- 27 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. 21 (4) , 3386-3395
A Novel Zero-Shot Learning Method With Feature Generation for Intelligent Fault Diagnosis
In the traditional data-driven fault diagnosis task, gathering training samples for all possible fault classes poses a significant challenge. There are many target faults that cannot be collected in advance, which potentially limiting the performance of fault diagnosis models. Zero-shot learning has emerged as a viable solution to this problem. However, it often encounters the issue of domain shift. In this article, an attribute-consistent generative adversarial network with feature generation (ACGAN-FG) is proposed for zero-shot fault diagnosis. ACGAN-FG introduces a discriminative classifier and a binary comparator to construct the attribute-consistent losses, which can alleviate the issue that the generated features may deviate from real faults. To generate fault features with greater diversity and enhance the robustness of the proposed model, a cycle rank loss is designed. Besides, this method also introduces feature concatenation to build new training data and testing data. This concatenation can transform the generated features into more discriminative representation for further fault diagnosis. The effectiveness of the proposed method is validated on two cases for fault diagnosis purpose. The results also indicate that the proposed method is outperforms other state-of-art zero-shot fault diagnosis methods.
- 27 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. 21 (4) , 3386-3395
A Novel Zero-Shot Learning Method With Feature Generation for Intelligent Fault Diagnosis
In the traditional data-driven fault diagnosis task, gathering training samples for all possible fault classes poses a significant challenge. There are many target faults that cannot be collected in advance, which potentially limiting the performance of fault diagnosis models. Zero-shot learning has emerged as a viable solution to this problem. However, it often encounters the issue of domain shift. In this article, an attribute-consistent generative adversarial network with feature generation (ACGAN-FG) is proposed for zero-shot fault diagnosis. ACGAN-FG introduces a discriminative classifier and a binary comparator to construct the attribute-consistent losses, which can alleviate the issue that the generated features may deviate from real faults. To generate fault features with greater diversity and enhance the robustness of the proposed model, a cycle rank loss is designed. Besides, this method also introduces feature concatenation to build new training data and testing data. This concatenation can transform the generated features into more discriminative representation for further fault diagnosis. The effectiveness of the proposed method is validated on two cases for fault diagnosis purpose. The results also indicate that the proposed method is outperforms other state-of-art zero-shot fault diagnosis methods.
- 29 July 2024
- Published by Taylor & Francis in International Journal of Human–Computer Interaction
- Vol. 41 (11) , 6515-6536
Enhancing Collaborative Shopping Experience Through Interactive Personalized Avatars and Shared Gaze in a Multi-User Augmented Reality Environment
- 29 July 2024
- Published by Taylor & Francis in International Journal of Human–Computer Interaction
- Vol. 41 (11) , 6515-6536
Enhancing Collaborative Shopping Experience Through Interactive Personalized Avatars and Shared Gaze in a Multi-User Augmented Reality Environment
- 15 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 73 (00189456) , 1-16
A Novel Approach for Intelligent Fault Diagnosis in Bearing With Imbalanced Data Based on Cycle-Consistent GAN
The rise of industrial progress has advanced the growth of deep learning (DL)-driven smart fault diagnosis techniques, particularly for condition-based maintenance (CBM). However, the training of these DL methods relies on large dataset, which is unrealistic to collect because fault signal is not practically viable in real case. To address this issue, this article proposes a conditional auxiliary classier cycle-consistent generative adversarial network restrained by Wasserstein distance with gradient penalty (CAC-CycleGAN-WGP). This model can generate superior-quality signals of the minority classes with stability from majority class. In the experimental section, a stacked autoencoder (AE)-based evaluator is proposed to evaluate the quality of these generated sample, and then imbalanced fault diagnosis is conducted at varying balance ratios based on two benchmarked datasets. The outcomes indicate that the proposed approach is adept at generating fault signals, leading to a notable enhancement in fault diagnosis accuracy as the generated samples are added. Additionally, the efficacy of the proposed framework was benchmarked against other commonly employed techniques. Among them, CAC-CycleGAN-WGP stands out with superior performance.
- 15 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 73 (00189456) , 1-16
A Novel Approach for Intelligent Fault Diagnosis in Bearing With Imbalanced Data Based on Cycle-Consistent GAN
The rise of industrial progress has advanced the growth of deep learning (DL)-driven smart fault diagnosis techniques, particularly for condition-based maintenance (CBM). However, the training of these DL methods relies on large dataset, which is unrealistic to collect because fault signal is not practically viable in real case. To address this issue, this article proposes a conditional auxiliary classier cycle-consistent generative adversarial network restrained by Wasserstein distance with gradient penalty (CAC-CycleGAN-WGP). This model can generate superior-quality signals of the minority classes with stability from majority class. In the experimental section, a stacked autoencoder (AE)-based evaluator is proposed to evaluate the quality of these generated sample, and then imbalanced fault diagnosis is conducted at varying balance ratios based on two benchmarked datasets. The outcomes indicate that the proposed approach is adept at generating fault signals, leading to a notable enhancement in fault diagnosis accuracy as the generated samples are added. Additionally, the efficacy of the proposed framework was benchmarked against other commonly employed techniques. Among them, CAC-CycleGAN-WGP stands out with superior performance.
- 1 June 2024
- Published by Springer Nature
- p. 116-127
Enhancing Remote Collaboration Through Drone-Driven Agent and Mixed Reality
- 1 June 2024
- Published by Springer Nature
- p. 116-127
Enhancing Remote Collaboration Through Drone-Driven Agent and Mixed Reality