Zhenrong Deng
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Zhenrong Deng has a total of 36 co-authors. Here are the top co-authors by number of shared publications:
- Rui Yang
Guangxi Key Laboratory of Images and Graphics Intelligent Processing, Guilin University of Electronic Technology, Guilin 541004, China
7 shared publications - Rushi Lan
Guilin University of Electronic Technology
6 shared publications - Xiaonan Luo
Guilin University of Electronic Technology, Guilin, China
5 shared publications Wenming Huang
Guilin University of Electronic Technology
3 shared publicationsPeizhi Wen
Guilin University of Electronic Technology
2 shared publicationsDengrui Hu
School of Computer Science and Information Security, Guilin University of Electronic Technology, Guilin, China
1 shared publication
Latest Publications
- Open Access
- 4 September 2025
- Published by MDPI AG in Mathematics
- Vol. 13 (17) , 2859
PowerStrand-YOLO: A High-Voltage Transmission Conductor Defect Detection Method for UAV Aerial Imagery
Broken or loose strands in high-voltage transmission conductors constitute critical defects that jeopardize grid reliability. Unmanned aerial vehicle (UAV) inspection has become indispensable for their timely discovery; however, conventional detectors falter in the face of cluttered backgrounds and the conductors’ diminutive pixel footprint, yielding sub-optimal accuracy and throughput. To overcome these limitations, we present PowerStrand-YOLO—an enhanced YOLOv8 derivative tailored for UAV imagery. The method is trained on a purpose-built dataset and integrates three technical contributions. (1) A C2f_DCNv4 module is introduced to strengthen multi-scale feature extraction. (2) An EMA attention mechanism is embedded to suppress background interference and emphasize defect-relevant cues. (3) The original loss function is superseded by Shape-IoU, compelling the network to attend closely to the geometric contours and spatial layout of strand anomalies. Extensive experiments demonstrate 95.4% precision, 96.2% recall, and 250 FPS. Relative to the baseline YOLOv8, PowerStrand-YOLO improves precision by 3% and recall by 6.8% while accelerating inference. Moreover, it also demonstrates competitive performance on the VisDrone2019 dataset. These results establish the improved framework as a more accurate and efficient solution for UAV-based inspection of power transmission lines.
- 4 September 2025
- Published by MDPI AG in Mathematics
- Vol. 13 (17) , 2859
Open AccessPowerStrand-YOLO: A High-Voltage Transmission Conductor Defect Detection Method for UAV Aerial Imagery
Broken or loose strands in high-voltage transmission conductors constitute critical defects that jeopardize grid reliability. Unmanned aerial vehicle (UAV) inspection has become indispensable for their timely discovery; however, conventional detectors falter in the face of cluttered backgrounds and the conductors’ diminutive pixel footprint, yielding sub-optimal accuracy and throughput. To overcome these limitations, we present PowerStrand-YOLO—an enhanced YOLOv8 derivative tailored for UAV imagery. The method is trained on a purpose-built dataset and integrates three technical contributions. (1) A C2f_DCNv4 module is introduced to strengthen multi-scale feature extraction. (2) An EMA attention mechanism is embedded to suppress background interference and emphasize defect-relevant cues. (3) The original loss function is superseded by Shape-IoU, compelling the network to attend closely to the geometric contours and spatial layout of strand anomalies. Extensive experiments demonstrate 95.4% precision, 96.2% recall, and 250 FPS. Relative to the baseline YOLOv8, PowerStrand-YOLO improves precision by 3% and recall by 6.8% while accelerating inference. Moreover, it also demonstrates competitive performance on the VisDrone2019 dataset. These results establish the improved framework as a more accurate and efficient solution for UAV-based inspection of power transmission lines.
- Open Access
- 29 May 2025
- Published by MDPI AG in Applied Sciences
- Vol. 15 (11) , 6117
RML-YOLO: An Insulator Defect Detection Method for UAV Aerial Images
The safety of power transmission lines is crucial to public well-being, with insulators being prone to failures such as self-detonation. However, images captured by unmanned aerial vehicles (UAVs) carrying optical sensors often face challenges, including uneven object scales, complex backgrounds, and difficulties in feature extraction due to distance, angles, and terrain. Additionally, conventional models are too large for UAV deployment. To address these issues, this paper proposes RML-YOLO, an improved insulator defect detection method based on YOLOv8. The approach introduces a tiered scale fusion feature (TSFF) module to enhance multi-scale detection accuracy by fusing features across network layers. Additionally, the multi-scale feature extraction network (MSFENet) is designed to prioritize large-scale features while adding an extra detection layer for small objects, improving multi-scale object detection precision. A lightweight multi-scale shared detection head (LMSHead) reduces model size and parameters by sharing features across layers, addressing scale distribution imbalances. Lastly, the receptive field attention channel attention convolution (RFCAConv) module aggregates features from various receptive fields to overcome the limitations of standard convolution. Experiments on the UID, SFID, and VISDrone 2019 datasets show that RML-YOLO outperforms YOLOv8n, reducing model size by 0.8 MB and parameters by 500,000, while improving AP by 7.8%, 2.74%, and 3.9%, respectively. These results demonstrate the method’s lightweight design, high detection performance, and strong generalization capability, making it suitable for deployment on UAVs with limited resources.
- 29 May 2025
- Published by MDPI AG in Applied Sciences
- Vol. 15 (11) , 6117
Open AccessRML-YOLO: An Insulator Defect Detection Method for UAV Aerial Images
The safety of power transmission lines is crucial to public well-being, with insulators being prone to failures such as self-detonation. However, images captured by unmanned aerial vehicles (UAVs) carrying optical sensors often face challenges, including uneven object scales, complex backgrounds, and difficulties in feature extraction due to distance, angles, and terrain. Additionally, conventional models are too large for UAV deployment. To address these issues, this paper proposes RML-YOLO, an improved insulator defect detection method based on YOLOv8. The approach introduces a tiered scale fusion feature (TSFF) module to enhance multi-scale detection accuracy by fusing features across network layers. Additionally, the multi-scale feature extraction network (MSFENet) is designed to prioritize large-scale features while adding an extra detection layer for small objects, improving multi-scale object detection precision. A lightweight multi-scale shared detection head (LMSHead) reduces model size and parameters by sharing features across layers, addressing scale distribution imbalances. Lastly, the receptive field attention channel attention convolution (RFCAConv) module aggregates features from various receptive fields to overcome the limitations of standard convolution. Experiments on the UID, SFID, and VISDrone 2019 datasets show that RML-YOLO outperforms YOLOv8n, reducing model size by 0.8 MB and parameters by 500,000, while improving AP by 7.8%, 2.74%, and 3.9%, respectively. These results demonstrate the method’s lightweight design, high detection performance, and strong generalization capability, making it suitable for deployment on UAVs with limited resources.
- Open Access
- 14 May 2025
- Published by Springer Nature in Research Square
LCJM: Joint Modeling of Multi-Intent Spoken Language Understanding with Label Attention and Chunk Partitioning
Spoken Language Understanding (SLU) is a critical task in natural language processing and human–computer interaction, consisting of intent detection and slot filling. However, multi‑intent utterances and complex semantic structures pose significant challenges, including error propagation, noise sensitivity in long utterances, and insufficient modeling of intent–slot interactions. To address these issues, we propose LCJM (Label‑Chunk Joint Model), a novel framework that integrates Label Attention and a Chunk‑based Sliding Window mechanism. Label Attention captures intent‑slot dependencies guided by corpus‑level priors, enhancing semantic consistency and mitigating the impact of mispredicted intents. The chunking strategy divides utterances into overlapping chunks, improving local context modeling and robustness to noisy or long inputs. Additionally, we incorporate a graph‑based label interaction network to model global semantic dependencies across tasks. Extensive experiments on two benchmark datasets, MixATIS and MixSNIPS, show that LCJM achieves superior performance in both intent detection and slot filling. These findings demonstrate that LCJM effectively balances global semantic integration and local contextual awareness, providing a cognitively inspired approach for robust multi‑intent SLU.
- 14 May 2025
- Published by Springer Nature in Research Square
Open AccessLCJM: Joint Modeling of Multi-Intent Spoken Language Understanding with Label Attention and Chunk Partitioning
Spoken Language Understanding (SLU) is a critical task in natural language processing and human–computer interaction, consisting of intent detection and slot filling. However, multi‑intent utterances and complex semantic structures pose significant challenges, including error propagation, noise sensitivity in long utterances, and insufficient modeling of intent–slot interactions. To address these issues, we propose LCJM (Label‑Chunk Joint Model), a novel framework that integrates Label Attention and a Chunk‑based Sliding Window mechanism. Label Attention captures intent‑slot dependencies guided by corpus‑level priors, enhancing semantic consistency and mitigating the impact of mispredicted intents. The chunking strategy divides utterances into overlapping chunks, improving local context modeling and robustness to noisy or long inputs. Additionally, we incorporate a graph‑based label interaction network to model global semantic dependencies across tasks. Extensive experiments on two benchmark datasets, MixATIS and MixSNIPS, show that LCJM achieves superior performance in both intent detection and slot filling. These findings demonstrate that LCJM effectively balances global semantic integration and local contextual awareness, providing a cognitively inspired approach for robust multi‑intent SLU.
- Open Access
- 6 January 2025
- Published by MDPI AG in Algorithms
- Vol. 18 (1) , 27
YOLO-TC: An Optimized Detection Model for Monitoring Safety-Critical Small Objects in Tower Crane Operations
Ensuring operational safety within high-risk environments, such as construction sites, is paramount, especially for tower crane operations where distractions can lead to severe accidents. Despite existing behavioral monitoring approaches, the task of identifying small yet hazardous objects like mobile phones and cigarettes in real time remains a significant challenge in ensuring operator compliance and site safety. Traditional object detection models often fall short in crane operator cabins due to complex lighting conditions, cluttered backgrounds, and the small physical scale of target objects. To address these challenges, we introduce YOLO-TC, a refined object detection model tailored specifically for tower crane monitoring applications. Built upon the robust YOLOv7 architecture, our model integrates a novel channel–spatial attention mechanism, ECA-CBAM, into the backbone network, enhancing feature extraction without an increase in parameter count. Additionally, we propose the HA-PANet architecture to achieve progressive feature fusion, addressing scale disparities and prioritizing small object detection while reducing noise from unrelated objects. To improve bounding box regression, the MPDIoU Loss function is employed, resulting in superior accuracy for small, critical objects in dense environments. The experimental results on both the PASCAL VOC benchmark and a custom dataset demonstrate that YOLO-TC outperforms baseline models, showcasing its robustness in identifying high-risk objects under challenging conditions. This model holds significant promise for enhancing automated safety monitoring, potentially reducing occupational hazards by providing a proactive, resilient solution for real-time risk detection in tower crane operations.
- 6 January 2025
- Published by MDPI AG in Algorithms
- Vol. 18 (1) , 27
Open AccessYOLO-TC: An Optimized Detection Model for Monitoring Safety-Critical Small Objects in Tower Crane Operations
Ensuring operational safety within high-risk environments, such as construction sites, is paramount, especially for tower crane operations where distractions can lead to severe accidents. Despite existing behavioral monitoring approaches, the task of identifying small yet hazardous objects like mobile phones and cigarettes in real time remains a significant challenge in ensuring operator compliance and site safety. Traditional object detection models often fall short in crane operator cabins due to complex lighting conditions, cluttered backgrounds, and the small physical scale of target objects. To address these challenges, we introduce YOLO-TC, a refined object detection model tailored specifically for tower crane monitoring applications. Built upon the robust YOLOv7 architecture, our model integrates a novel channel–spatial attention mechanism, ECA-CBAM, into the backbone network, enhancing feature extraction without an increase in parameter count. Additionally, we propose the HA-PANet architecture to achieve progressive feature fusion, addressing scale disparities and prioritizing small object detection while reducing noise from unrelated objects. To improve bounding box regression, the MPDIoU Loss function is employed, resulting in superior accuracy for small, critical objects in dense environments. The experimental results on both the PASCAL VOC benchmark and a custom dataset demonstrate that YOLO-TC outperforms baseline models, showcasing its robustness in identifying high-risk objects under challenging conditions. This model holds significant promise for enhancing automated safety monitoring, potentially reducing occupational hazards by providing a proactive, resilient solution for real-time risk detection in tower crane operations.
- Open Access
- 26 December 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Multimedia Computing, Communications, and Applications
- Vol. 21 (2) , 1-22
Deepfake Video Detection Using Facial Feature Points and Ch-Transformer
With the development of Metaverse technology, the avatar in Metaverse has faced serious security and privacy concerns. Analyzing facial features to distinguish between genuine and manipulated facial videos holds significant research importance for ensuring the authenticity of characters in the virtual world and for mitigating discrimination as well as preventing malicious use of facial data. To address this issue, the Facial Feature Points and Class-head-Transformer (FFP-ChT) deepfake video detection model is designed based on the clues of different FFPs distribution in real and fake videos and different displacement distances of real and fake FFPs between frames. The face video input is first detected by the BlazeFace model, and the face detection results are fed into the FaceMesh model to extract 468 FFPs. Then, the Lucas–Kanade (LK) optical flow method is used to track the points of the face, the face calibration algorithm is introduced to re-calibrate the FFPs, and the jitter displacement is calculated by tracking the FFPs between frames. Finally, the Ch is designed in the transformer, and the FFPs and FFP displacement are jointly classified through the ChT model. In this way, the designed ChT classifier is able to accurately and effectively identify deepfake videos. Experiments on open datasets clearly demonstrate the effectiveness and generalization capabilities of our approach.
- 26 December 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Multimedia Computing, Communications, and Applications
- Vol. 21 (2) , 1-22
Open AccessDeepfake Video Detection Using Facial Feature Points and Ch-Transformer
With the development of Metaverse technology, the avatar in Metaverse has faced serious security and privacy concerns. Analyzing facial features to distinguish between genuine and manipulated facial videos holds significant research importance for ensuring the authenticity of characters in the virtual world and for mitigating discrimination as well as preventing malicious use of facial data. To address this issue, the Facial Feature Points and Class-head-Transformer (FFP-ChT) deepfake video detection model is designed based on the clues of different FFPs distribution in real and fake videos and different displacement distances of real and fake FFPs between frames. The face video input is first detected by the BlazeFace model, and the face detection results are fed into the FaceMesh model to extract 468 FFPs. Then, the Lucas–Kanade (LK) optical flow method is used to track the points of the face, the face calibration algorithm is introduced to re-calibrate the FFPs, and the jitter displacement is calculated by tracking the FFPs between frames. Finally, the Ch is designed in the transformer, and the FFPs and FFP displacement are jointly classified through the ChT model. In this way, the designed ChT classifier is able to accurately and effectively identify deepfake videos. Experiments on open datasets clearly demonstrate the effectiveness and generalization capabilities of our approach.
- Open Access
- 30 August 2024
- Published by MDPI AG in Mathematics
- Vol. 12 (17) , 2714
KCB-FLAT: Enhancing Chinese Named Entity Recognition with Syntactic Information and Boundary Smoothing Techniques
Named entity recognition (NER) is a fundamental task in Natural Language Processing (NLP). During the training process, NER models suffer from over-confidence, and especially for the Chinese NER task, it involves word segmentation and introduces erroneous entity boundary segmentation, exacerbating over-confidence and reducing the model’s overall performance. These issues limit further enhancement of NER models. To tackle these problems, we proposes a new model named KCB-FLAT, designed to enhance Chinese NER performance by integrating enriched semantic information with the word-Boundary Smoothing technique. Particularly, we first extract various types of syntactic data and utilize a network named Key-Value Memory Network, based on syntactic information to functionalize this, integrating it through an attention mechanism to generate syntactic feature embeddings for Chinese characters. Subsequently, we employed an encoder named Cross-Transformer to thoroughly combine syntactic and lexical information to address the entity boundary segmentation errors caused by lexical information. Finally, we introduce a Boundary Smoothing module, combined with a regularity-conscious function, to capture the internal regularity of per entity, reducing the model’s overconfidence in entity probabilities through smoothing. Experimental results demonstrate that the proposed model achieves exceptional performance on the MSRA, Resume, Weibo, and self-built ZJ datasets, as verified by the F1 score.
- 30 August 2024
- Published by MDPI AG in Mathematics
- Vol. 12 (17) , 2714
Open AccessKCB-FLAT: Enhancing Chinese Named Entity Recognition with Syntactic Information and Boundary Smoothing Techniques
Named entity recognition (NER) is a fundamental task in Natural Language Processing (NLP). During the training process, NER models suffer from over-confidence, and especially for the Chinese NER task, it involves word segmentation and introduces erroneous entity boundary segmentation, exacerbating over-confidence and reducing the model’s overall performance. These issues limit further enhancement of NER models. To tackle these problems, we proposes a new model named KCB-FLAT, designed to enhance Chinese NER performance by integrating enriched semantic information with the word-Boundary Smoothing technique. Particularly, we first extract various types of syntactic data and utilize a network named Key-Value Memory Network, based on syntactic information to functionalize this, integrating it through an attention mechanism to generate syntactic feature embeddings for Chinese characters. Subsequently, we employed an encoder named Cross-Transformer to thoroughly combine syntactic and lexical information to address the entity boundary segmentation errors caused by lexical information. Finally, we introduce a Boundary Smoothing module, combined with a regularity-conscious function, to capture the internal regularity of per entity, reducing the model’s overconfidence in entity probabilities through smoothing. Experimental results demonstrate that the proposed model achieves exceptional performance on the MSRA, Resume, Weibo, and self-built ZJ datasets, as verified by the F1 score.
- 19 March 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Letters
- Vol. 31 (10709908) , 914-918
4DPM: Deepfake Detection With a Denoising Diffusion Probabilistic Mask
In the face of increasingly realistic fake human faces, research on enhancing the differences between real and fake images is valuable for improving the generalization capabilities of fake face detection models. In this letter, we propose a method called DPMask (Diffusion Probabilistic Mask) to amplify the distinctions between authentic and counterfeit human facial images. Specifically, we use a dataset consisting of real human facial images and Simplex noise to train a denoising diffusion probabilistic model for the proposed DPMask. Subsequently, we separately apply the DPMask and U-Net to real and fake human facial images to create noticeably distinct genuine and counterfeit human facial images. A lightweight classification network blue is further designed based on RepVGG to classify the newly generated real and fake human faces. Experimental results demonstrate that our model achieves high accuracy on a manually created fake face dataset (RFFD), a GAN-generated fake face dataset (Seq-DeepFake), and a DDPM-generated face dataset (HiFi-IFDL). Furthermore, the addition of DPMask significantly improves the performance of some public fake face detection models.
- 19 March 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Letters
- Vol. 31 (10709908) , 914-918
4DPM: Deepfake Detection With a Denoising Diffusion Probabilistic Mask
In the face of increasingly realistic fake human faces, research on enhancing the differences between real and fake images is valuable for improving the generalization capabilities of fake face detection models. In this letter, we propose a method called DPMask (Diffusion Probabilistic Mask) to amplify the distinctions between authentic and counterfeit human facial images. Specifically, we use a dataset consisting of real human facial images and Simplex noise to train a denoising diffusion probabilistic model for the proposed DPMask. Subsequently, we separately apply the DPMask and U-Net to real and fake human facial images to create noticeably distinct genuine and counterfeit human facial images. A lightweight classification network blue is further designed based on RepVGG to classify the newly generated real and fake human faces. Experimental results demonstrate that our model achieves high accuracy on a manually created fake face dataset (RFFD), a GAN-generated fake face dataset (Seq-DeepFake), and a DDPM-generated face dataset (HiFi-IFDL). Furthermore, the addition of DPMask significantly improves the performance of some public fake face detection models.
- 1 March 2024
- Published by Springer Nature
- p. 133-143
Smart Power Safety Hazard Inspection System Based on YOLOv7
- 1 March 2024
- Published by Springer Nature
- p. 133-143
Smart Power Safety Hazard Inspection System Based on YOLOv7
- Open Access
Kcr-FLAT: A Chinese-Named Entity Recognition Model with Enhanced Semantic Information
The performance of Chinese-named entity recognition (NER) has improved via word enhancement or new frameworks that incorporate various types of external data. However, for Chinese NER, syntactic composition (in sentence level) and inner regularity (in character-level) have rarely been studied. Chinese characters are highly sensitive to sentential syntactic data. The same Chinese character sequence can be decomposed into different combinations of words according to how they are used and placed in the context. In addition, the same type of entities usually have the same naming rules due to the specificity of the Chinese language structure. This paper presents a Kcr-FLAT to improve the performance of Chinese NER with enhanced semantic information. Specifically, we first extract different types of syntactic data, functionalize the syntactic information by a key-value memory network (KVMN), and fuse them by attention mechanism. Then the syntactic information and lexical information are integrated by a cross-transformer. Finally, we use an inner regularity perception module to capture the internal regularity of each entity for better entity type prediction. The experimental results show that with F1 scores as the evaluation index, the proposed model obtains 96.51%, 96.81%, and 70.12% accuracy rates on MSRA, resume, and Weibo datasets, respectively.
Open AccessKcr-FLAT: A Chinese-Named Entity Recognition Model with Enhanced Semantic Information
The performance of Chinese-named entity recognition (NER) has improved via word enhancement or new frameworks that incorporate various types of external data. However, for Chinese NER, syntactic composition (in sentence level) and inner regularity (in character-level) have rarely been studied. Chinese characters are highly sensitive to sentential syntactic data. The same Chinese character sequence can be decomposed into different combinations of words according to how they are used and placed in the context. In addition, the same type of entities usually have the same naming rules due to the specificity of the Chinese language structure. This paper presents a Kcr-FLAT to improve the performance of Chinese NER with enhanced semantic information. Specifically, we first extract different types of syntactic data, functionalize the syntactic information by a key-value memory network (KVMN), and fuse them by attention mechanism. Then the syntactic information and lexical information are integrated by a cross-transformer. Finally, we use an inner regularity perception module to capture the internal regularity of each entity for better entity type prediction. The experimental results show that with F1 scores as the evaluation index, the proposed model obtains 96.51%, 96.81%, and 70.12% accuracy rates on MSRA, resume, and Weibo datasets, respectively.
- Open Access
- 26 December 2020
- Published by Wiley in Wireless Communications and Mobile Computing
- Vol. 2020, 1-10
Emotional Dialogue Generation Based on Conditional Variational Autoencoder and Dual Emotion Framework
An excellent dialogue system needs to not only generate rich and diverse logical responses but also meet the needs of users for emotional communication. However, despite much work, these two problems have not been solved. In this paper, we propose a model based on conditional variational autoencoder and dual emotion framework (CVAE-DE) to generate emotional responses. In our model, latent variables of the conditional variational autoencoder are adopted to promote the diversity of conversation. A dual emotion framework is adopted to control the explicit emotion of the response and prevent the conversation from generating emotion drift indicating that the emotion of the response is not related to the input sentence. A multiclass emotion classifier based on the Bidirectional Encoder Representations from Transformers (BERT) model is employed to obtain emotion labels, which promotes the accuracy of emotion recognition and emotion expression. A large number of experiments show that our model not only generates rich and diverse responses but also is emotionally coherent and controllable.
- 26 December 2020
- Published by Wiley in Wireless Communications and Mobile Computing
- Vol. 2020, 1-10
Open AccessEmotional Dialogue Generation Based on Conditional Variational Autoencoder and Dual Emotion Framework
An excellent dialogue system needs to not only generate rich and diverse logical responses but also meet the needs of users for emotional communication. However, despite much work, these two problems have not been solved. In this paper, we propose a model based on conditional variational autoencoder and dual emotion framework (CVAE-DE) to generate emotional responses. In our model, latent variables of the conditional variational autoencoder are adopted to promote the diversity of conversation. A dual emotion framework is adopted to control the explicit emotion of the response and prevent the conversation from generating emotion drift indicating that the emotion of the response is not related to the input sentence. A multiclass emotion classifier based on the Bidirectional Encoder Representations from Transformers (BERT) model is employed to obtain emotion labels, which promotes the accuracy of emotion recognition and emotion expression. A large number of experiments show that our model not only generates rich and diverse responses but also is emotionally coherent and controllable.