Weichao Cai
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Weichao Cai has a total of 22 co-authors. Here are the top co-authors by number of shared publications:
- Chao Huang
Sun Yat-Sen University, Shenzhen, CHINA
5 shared publications - Bob Zhang
University of Macau, Macau SAR, China
4 shared publications - Weiliang Huang
University of Macau, Macau, Macao
4 shared publications - Biao Xue
Xiamen University, Xiamen, China
3 shared publications - Fei Yuan
School of Informatics, Xiamen University, Xiamen, China
2 shared publications - Jingwen Yan
College of Engineering, Shantou University, Shantou, China
2 shared publications
Latest Publications
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 3493-3501
UPR-VAD: U ncertainty-guided Signal P urification and R egularization for Weakly-Supervised V ideo A nomaly D etection
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 3493-3501
Open AccessUPR-VAD: U ncertainty-guided Signal P urification and R egularization for Weakly-Supervised V ideo A nomaly D etection
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 3483-3492
Customized Anomalous Video Generation for Incremental Learning in Weakly-Supervised Video Anomaly Detection
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 3483-3492
Open AccessCustomized Anomalous Video Generation for Incremental Learning in Weakly-Supervised Video Anomaly Detection
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 115-124
Bio-PCNet: Biologically-inspired Predictive Coding Network for Multi-modal Maritime Segmentation under Composite Degradation
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 115-124
Open AccessBio-PCNet: Biologically-inspired Predictive Coding Network for Multi-modal Maritime Segmentation under Composite Degradation
- 5 June 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. PP (10518215) , 1
HEPE++: Towards VLM-based Hybrid Explainable Prompt Enhancement for Zero-Shot Industrial Anomaly Detection
Zero-Shot Industrial Anomaly Detection (ZSIAD) aims to identify and localize anomalies in industrial images from unseen categories. Owing to the powerful generalization capabilities, Vision-Language Models (VLMs) have achieved growing interest in ZSIAD. To guide the model toward understanding and localizing the semantically complex industrial anomalies, existing VLM-based methods have attempted to provide additional prompts to the model through learnable text prompt templates. However, these zero-shot methods lack detailed descriptions of specific anomalies, making it difficult to classify and segment the diverse range of industrial anomalies accurately. To address the aforementioned issue, we propose an effective solution, which includes a multi-stage prompt generation agent and a Hybrid Explainable Prompt Enhancement plus (HEPE++) framework. Specifically, we leverage the Multi-modal Language Large Model (MLLM) to articulate the detailed differential information between normal and test samples, which can provide detailed text prompts to the model through further refinement and anti-false alarm constraint. Moreover, we introduce the Visual Fundamental Model (VFM) to generate anomaly-related attention prompts for more accurate localization of anomalies with varying sizes and shapes. Building on this foundation, HEPE++ jointly utilizes generated detailed text and attention prompts to enhance the performance of VLM-based methods in ZSIAD. Furthermore, we introduce a novel gated attention mechanism to augment the model’s ability to focus on potential subtle anomalous regions in the foreground. Extensive experiments on seven real-world industrial anomaly detection datasets have shown that the proposed method not only outperforms recent SOTA methods, but also its explainable prompts provide the model with a more intuitive basis for anomaly identification.
- 5 June 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. PP (10518215) , 1
HEPE++: Towards VLM-based Hybrid Explainable Prompt Enhancement for Zero-Shot Industrial Anomaly Detection
Zero-Shot Industrial Anomaly Detection (ZSIAD) aims to identify and localize anomalies in industrial images from unseen categories. Owing to the powerful generalization capabilities, Vision-Language Models (VLMs) have achieved growing interest in ZSIAD. To guide the model toward understanding and localizing the semantically complex industrial anomalies, existing VLM-based methods have attempted to provide additional prompts to the model through learnable text prompt templates. However, these zero-shot methods lack detailed descriptions of specific anomalies, making it difficult to classify and segment the diverse range of industrial anomalies accurately. To address the aforementioned issue, we propose an effective solution, which includes a multi-stage prompt generation agent and a Hybrid Explainable Prompt Enhancement plus (HEPE++) framework. Specifically, we leverage the Multi-modal Language Large Model (MLLM) to articulate the detailed differential information between normal and test samples, which can provide detailed text prompts to the model through further refinement and anti-false alarm constraint. Moreover, we introduce the Visual Fundamental Model (VFM) to generate anomaly-related attention prompts for more accurate localization of anomalies with varying sizes and shapes. Building on this foundation, HEPE++ jointly utilizes generated detailed text and attention prompts to enhance the performance of VLM-based methods in ZSIAD. Furthermore, we introduce a novel gated attention mechanism to augment the model’s ability to focus on potential subtle anomalous regions in the foreground. Extensive experiments on seven real-world industrial anomaly detection datasets have shown that the proposed method not only outperforms recent SOTA methods, but also its explainable prompts provide the model with a more intuitive basis for anomaly identification.
- 24 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 74 (00189456) , 1-12
A State Space Model-Driven Multiscale Attention Method for Geological Hazard Segmentation
High-precision segmentation of geological disasters plays a crucial role in disaster rescue, significantly contributing to improving rescue efficiency and optimizing the allocation of rescue resources. However, landslides and debris flows typically have irregular contours and arbitrary scopes, which cause most existing methods to suffer from poor performance. To address these issues, we propose a novel dual-path feature extraction architecture for geological hazard segmentation. Firstly, the State Space Model Driven Global Multi-scale Attention module (SSMGMA) is used to model cross-scale long-range dependencies by powerful multi-scale representation. Dilated convolutions are adopted to extract multi-scale features, while the state space model is incorporated to capture the global context and model cross-scale long-range dependencies. Consequently, the SSMGMA allows the proposed model to completely segment geological disasters. Subsequently, the High-Frequency Prompt Encoder module (HFPE) is employed to alleviate the negative effects caused by irregular contour problems. The core idea of the HFPE is to effectively encode high-frequency information as the prompt to the decoder. Specifically, a well-designed encoding strategy is adopted in the HFPE, which can transform subtle variations in high-frequency information into precise locations of disaster areas. By combining the SSMGMA and HFPE, the proposed dual-path architecture leverages the advantages of multi-scale features and high-frequency feature encoding, significantly improving the accuracy of disaster segmentation. Experimental results show that the proposed method has superior performance.
- 24 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 74 (00189456) , 1-12
A State Space Model-Driven Multiscale Attention Method for Geological Hazard Segmentation
High-precision segmentation of geological disasters plays a crucial role in disaster rescue, significantly contributing to improving rescue efficiency and optimizing the allocation of rescue resources. However, landslides and debris flows typically have irregular contours and arbitrary scopes, which cause most existing methods to suffer from poor performance. To address these issues, we propose a novel dual-path feature extraction architecture for geological hazard segmentation. Firstly, the State Space Model Driven Global Multi-scale Attention module (SSMGMA) is used to model cross-scale long-range dependencies by powerful multi-scale representation. Dilated convolutions are adopted to extract multi-scale features, while the state space model is incorporated to capture the global context and model cross-scale long-range dependencies. Consequently, the SSMGMA allows the proposed model to completely segment geological disasters. Subsequently, the High-Frequency Prompt Encoder module (HFPE) is employed to alleviate the negative effects caused by irregular contour problems. The core idea of the HFPE is to effectively encode high-frequency information as the prompt to the decoder. Specifically, a well-designed encoding strategy is adopted in the HFPE, which can transform subtle variations in high-frequency information into precise locations of disaster areas. By combining the SSMGMA and HFPE, the proposed dual-path architecture leverages the advantages of multi-scale features and high-frequency feature encoding, significantly improving the accuracy of disaster segmentation. Experimental results show that the proposed method has superior performance.
- 4 April 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 24 (10) , 16961-16971
Multiscale Global Attention for Abnormal Geological Hazard Segmentation
Accurately segmenting geological hazard areas in high-resolution remote sensing images faces challenges due to the arbitrary scopes and irregular contours of these areas. In this paper, we propose a novel method for abnormal geological region segmentation in high-resolution remote sensing images. Specifically, the proposed method consists of two modules: Channel Transformer Encoder Module (CTEM) and Multi-scale Global Attention Module (MSGAM). On the one hand, MSGAM is designed to effectively utilize low and high-level features. To this end, it fuses multi-scale representations extracted via dilated convolutions with varying dilation rates. To model long-range multi-scale dependencies, CTEM is enabled to automatically assign importance weights to multi-scale features and adapt receptive fields accordingly. In this way, our method can address the limited global context of convolutional operations. The proposed method achieves state-of-the-art results on the dataset of landslide and debris flow disasters. Experimental results demonstrate the effectiveness and superiority of the proposed method in handling irregular contours and shapes of abnormal geological regions.
- 4 April 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 24 (10) , 16961-16971
Multiscale Global Attention for Abnormal Geological Hazard Segmentation
Accurately segmenting geological hazard areas in high-resolution remote sensing images faces challenges due to the arbitrary scopes and irregular contours of these areas. In this paper, we propose a novel method for abnormal geological region segmentation in high-resolution remote sensing images. Specifically, the proposed method consists of two modules: Channel Transformer Encoder Module (CTEM) and Multi-scale Global Attention Module (MSGAM). On the one hand, MSGAM is designed to effectively utilize low and high-level features. To this end, it fuses multi-scale representations extracted via dilated convolutions with varying dilation rates. To model long-range multi-scale dependencies, CTEM is enabled to automatically assign importance weights to multi-scale features and adapt receptive fields accordingly. In this way, our method can address the limited global context of convolutional operations. The proposed method achieves state-of-the-art results on the dataset of landslide and debris flow disasters. Experimental results demonstrate the effectiveness and superiority of the proposed method in handling irregular contours and shapes of abnormal geological regions.