wen-dong Jiang

Dr. wen-dong Jiang

orcid

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
6 February 2025 in Expert Systems with Applications
Verified
Journal Article
Closed access
Yue-Shi LeeYue-Shi Lee
Yue-Shi Lee
Show-Jane YenShow-Jane Yen
Show-Jane Yen
wen-dong Jiangwen-dong Jiang
wen-dong Jiang
JCJiyuan Chen
Jiyuan Chen
CCChih-Yung Chang
Chih-Yung Chang

23 March 2025 in Information Processing & Management
Verified
Journal Article
Closed access
wen-dong Jiangwen-dong Jiang
wen-dong Jiang
CCChih-Yung Chang
Chih-Yung Chang
SYShow-Jane Yen
Show-Jane Yen
SWShih-Jung Wu
Shih-Jung Wu
DRDiptendu Sinha Roy
Diptendu Sinha Roy

24 June 2025 in IEEE Transactions on Systems, Man, and Cybernetics: Systems
Verified
Journal Article
Closed access
wen-dong Jiangwen-dong Jiang
wen-dong Jiang
CCChih-Yung Chang
Chih-Yung Chang
MSMing-Yang Su
Ming-Yang Su
Yue-Shi LeeYue-Shi Lee
Yue-Shi Lee
DRDiptendu Sinha Roy
Diptendu Sinha Roy
Social violence presents a compelling challenge to public safety, yet existing multimodal detection systems exhibit excessive reliance on RGB image semantics and opaque decision-making processes. Despite leveraging visual and auditory data, current models demonstrate RGB bias in feature prioritization, as evidenced by explainability analyzes, thereby limiting their generalization for behavioral understanding. Additionally, modality inconsistency and inefficient fusion mechanisms impair model transparency and training stability. To bridge these gaps, this study proposes modality-aligned preprocessing (VAJ) that structurally unifies visual-auditory features through conflict resolution and input optimization, explicitly suppressing color dominance while enhancing interpretable feature representations. Complementing this, we design DTVDS, an interpretable detection framework integrating knowledge distillation to transfer distilled behavioral insights from a cumbersome teacher network to an efficient student model. This dual strategy not only addresses computational overhead but also clarifies decision logic through simplified inference pathways. Evaluations on XD-Violence and UCF-Crime benchmarks demonstrate superior performance, with AP (89.64%) and AUC (88.35%) outperforming existing methods. Qualitative evaluations further validate interpretability, revealing modality-coherent attention maps and human-aligned rationale visualization. The proposed method advances violence detection by addressing persistent shortcomings in multimodal alignment and model explainability.

28 January 2026 in IEEE Transactions on Emerging Topics in Computational Intelligence
Verified
Journal Article
Closed access
CCChih-Yung Chang
Chih-Yung Chang
wen-dong Jiangwen-dong Jiang
wen-dong Jiang
ICI-Hsiung Chang
I-Hsiung Chang
DRDiptendu Sinha Roy
Diptendu Sinha Roy
Anomaly detection is often formulated as a Multiple Instance Learning (MIL) problem, where an anomaly detector learns to generate frame-level anomaly scores under multi-modal supervision. However, most previous studies have two drawbacks: 1) the feature fusion between attributes overlooks the model’s interpretability; and 2) the training strategy based on pre-trained models leads to excessively long training times. To address these issues, this paper proposes an Interpretable Multi-modal Anomaly Detection System called IMADS. The proposed IMADS abandons the traditional multi-modal fusion approach and adopts single-modal training with late-stage decision fusion optimized by Bayesian techniques to resolve the interpretability problem caused by traditional feature fusion. Moreover, the proposed IMADS introduces a transfer learning method from frame-level to video-level, which essentially adds a temporal dimension to the 2D-to-3D conversion by randomizing parameters along the time dimension during training. This approach not only improves training efficiency but also ensures the model’s interpretability. Experimental results demonstrate that the proposed IMADS significantly outperforms existing methods in terms of performance, proving its innovativeness and effectiveness.

21 January 2026 in IEEE Transactions on Systems, Man, and Cybernetics: Systems
Verified
Journal Article
Closed access
wen-dong Jiangwen-dong Jiang
wen-dong Jiang
YCYu-Ting Chin
Yu-Ting Chin
YYYu-Ting Yang
Yu-Ting Yang
CCChih-Yung Chang
Chih-Yung Chang
DRDiptendu Sinha Roy
Diptendu Sinha Roy
Recently, violence detection systems developed using unified multimodal models have achieved significant success and attracted widespread attention. However, most of them typically suffer from two major issues: lack of interpretability as opaque models and limited functionality, providing only classification or retrieval capabilities. This article proposes a novel interpretable violence detection system called the three-in-one (TIO) system to address these challenges. The proposed TIO system integrates knowledge graphs (KGs) and graph attention networks (GATs) to achieve three core functionalities: detection, retrieval, and explanation. Specifically, the system processes each video frame along with text descriptions generated by a large language model (LLM) for a given video containing potential violent behavior. It employs ImageBind to create high-dimensional embeddings for constructing a KG. Subsequently, the system uses GAT for reasoning, applies light time series modules to extract video embedding features, and finally connects a classifier and retriever for multifunctional output. Leveraging the interpretability of KG, the system verifies the rationale behind each output during the reasoning process. In addition, this article proposes a kernel function-adjusted distance-based computation method to reduce the computational complexity of the TIO system. Extensive experiments conducted on the XD-Violence, UCF-Crime, and UCFCrime-AR datasets demonstrate the effectiveness of the proposed TIO system.

27 February 2026 in IEEE Transactions on Big Data
Verified
Journal Article
Closed access
wen-dong Jiangwen-dong Jiang
wen-dong Jiang
CCChih-Yung Chang
Chih-Yung Chang
THTzu-Chia Huang
Tzu-Chia Huang
YCYu-Ting Chin
Yu-Ting Chin
DRDiptendu Sinha Roy
Diptendu Sinha Roy
The proliferation of big data has fueled the success of deep learning; however, its inherent ”black box” nature poses significant challenges for its adoption in safety-critical domains. Existing interpretable machine learning methods offer partial solutions but often struggle with model fidelity, inconsistent explanations, a lack of holistic model understanding, and critically, computational inefficiency, especially when applied to models trained on large-scale datasets. To overcome these hurdles, this paper introduces Parallel Explainer (PEXP), an innovative parallel tree-based interpretation framework designed for scalability and comprehensive understanding. PEXP initiates by generating a localized sample set around a target instance through data distribution-aware perturbations. It then computes similarity scores and employs a kernel function to weight these samples effectively. Leveraging concepts from Bagging and Boosting, PEXP efficiently constructs Parallel Ensemble Trees as its core interpretable model. This model provides feature importance-based explanations and aggregates insights across all samples to achieve a global understanding of the model's behavior on the entire dataset. Experimental results demonstrate PEXP's significant advantages over mainstream interpretable methods in both runtime efficiency and the quality of explanations, particularly crucial for big data analytics. Furthermore, a case study illustrates PEXP's application in enhancing the interpretability of video anomaly detection systems within smart cities, a domain characterized by large volumes of data and offers insights for improving Transformer-based architectures.