Kebing Jin
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Kebing Jin has a total of 49 co-authors. Here are the top co-authors by number of shared publications:
- Hankz Hankui Zhuo
National Key Laboratory for Novel Software Technology, Nanjing University, China
5 shared publications - Jianhang Tang
Guizhou University
4 shared publications - Yang Zhang
College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing, China
4 shared publications - Jinghui Qin
Guangdong University of Technology, Guangzhou, China
3 shared publications - Jiangtian Nie
University of Aberdeen
2 shared publications Yixiong Feng
School of Mechanical Engineering, Guizhou University, Guiyang, China
2 shared publications
Latest Publications
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 15301-15310
ISPCloak: Weaponizing ISP for Optimization-Free Physical Camouflage against Deepfake Detectors
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 15301-15310
Open AccessISPCloak: Weaponizing ISP for Optimization-Free Physical Camouflage against Deepfake Detectors
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 1870-1879
EmoAgent-R1:Towards Multimodal Emotion Understanding with Reinforcement Learning-based Dynamic Agent Specialization
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 1870-1879
Open AccessEmoAgent-R1:Towards Multimodal Emotion Understanding with Reinforcement Learning-based Dynamic Agent Specialization
- Open Access
- 7 October 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Intelligent Systems and Technology
A Sequential Condition Evolution and Interaction Knowledge Graph Framework for Traditional Chinese Medicine Recommendation
The ancient art of Traditional Chinese Medicine (TCM) is distinguished by its extensive annals of utilizing nature's botanical emissaries to ameliorate various pathological conditions. TCM diagnosis and treatment exhibit a pronounced degree of personalization and an organically holistic approach, necessitating a comprehensive consideration of the patient's evolving physiological and symptomatic states over temporal domains. However, existing methods for TCM recommendation represent a flaw in accounting for the dynamic oscillations in patients’ conditions, instead restricting their explorations to potential correlative patterns between symptomatic presentations and prescribed remedies. In this paper, we propose a novel approach for optimizing TCM recommendations based on Sequential Condition Evolution and Interaction Knowledge Graphs SCEIKG , an innovation framework that conceptualizes the method as a sequential prescription-making problem by considering the inherent dynamism of patients’ conditions across multiple diagnoses. Furthermore, we incorporate an interaction knowledge graph to enhance the accuracy of recommendations by considering the intricate interplay between various herbs and patients’ states. Experimental results on the real-world dataset demonstrate that our approach outperforms existing TCM recommendation methods, achieving state-of-the-art performance. The source code of SCEIKG is available at https://github.com/jzephyrl/SCEIKG-TCM .
- 7 October 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Intelligent Systems and Technology
Open AccessA Sequential Condition Evolution and Interaction Knowledge Graph Framework for Traditional Chinese Medicine Recommendation
The ancient art of Traditional Chinese Medicine (TCM) is distinguished by its extensive annals of utilizing nature's botanical emissaries to ameliorate various pathological conditions. TCM diagnosis and treatment exhibit a pronounced degree of personalization and an organically holistic approach, necessitating a comprehensive consideration of the patient's evolving physiological and symptomatic states over temporal domains. However, existing methods for TCM recommendation represent a flaw in accounting for the dynamic oscillations in patients’ conditions, instead restricting their explorations to potential correlative patterns between symptomatic presentations and prescribed remedies. In this paper, we propose a novel approach for optimizing TCM recommendations based on Sequential Condition Evolution and Interaction Knowledge Graphs SCEIKG , an innovation framework that conceptualizes the method as a sequential prescription-making problem by considering the inherent dynamism of patients’ conditions across multiple diagnoses. Furthermore, we incorporate an interaction knowledge graph to enhance the accuracy of recommendations by considering the intricate interplay between various herbs and patients’ states. Experimental results on the real-world dataset demonstrate that our approach outperforms existing TCM recommendation methods, achieving state-of-the-art performance. The source code of SCEIKG is available at https://github.com/jzephyrl/SCEIKG-TCM .
- 14 August 2026
- Published by Elsevier in Expert Systems with Applications
- Vol. 333
A multi-agent comprehensive Judge for mixed-source multimodal misinformation detection
- 14 August 2026
- Published by Elsevier in Expert Systems with Applications
- Vol. 333
A multi-agent comprehensive Judge for mixed-source multimodal misinformation detection
- Open Access
- 26 June 2026
- Published by Elsevier in SSRN Electronic Journal
An unsupervised federated anomaly detection framework for UAV swarms with memory network and contrastive learning enhanced spatiotemporal autoencoder
The large-scale deployment of unmanned aerial vehicle (UAV) swarms has created an urgent need for their safe and reliable operation. However, data privacy constraints, high communication costs, and heavy computational burdens with centralized training limit the applicability of existing methods to distributed collaborative anomaly detection (AD) in UAV swarms. To address this, we propose an unsupervised federated AD framework for UAV swarms with memory networks and contrastive learning enhanced spatiotemporal autoencoder (MN-CL-STAE). Specifically, we design a lightweight spatiotemporal encoder model based on a multi-scale temporal convolutional network (MSTCN) and a convolutional neural network (CNN) to fully capture complex spatiotemporal features in normal flight data. Building on this foundation, memory network enhancement strategy models prototypes of spatiotemporal encoded features, adaptively extracting key memory features to gate residual injection into the decoder. This improves the model’s ability to stably represent normal patterns and mitigates excessive anomaly reconstruction caused by random noise. Concurrently, multi-view contrastive learning constrains the model to learn locally invariant representations under normal patterns, promoting compact clustering of normal samples and thereby improving the separability and discriminability of anomalies. Overall, under the federated learning framework, this paper adopts the federated averaging (FedAvg) algorithm to aggregate client model parameters for global collaborative optimization, thereby realizing distributed AD for UAV swarms while protecting local data privacy. Extensive experimental results on the ALFA dataset demonstrate that the proposed method significantly outperforms various representative methods in AD tasks.
- 26 June 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessAn unsupervised federated anomaly detection framework for UAV swarms with memory network and contrastive learning enhanced spatiotemporal autoencoder
The large-scale deployment of unmanned aerial vehicle (UAV) swarms has created an urgent need for their safe and reliable operation. However, data privacy constraints, high communication costs, and heavy computational burdens with centralized training limit the applicability of existing methods to distributed collaborative anomaly detection (AD) in UAV swarms. To address this, we propose an unsupervised federated AD framework for UAV swarms with memory networks and contrastive learning enhanced spatiotemporal autoencoder (MN-CL-STAE). Specifically, we design a lightweight spatiotemporal encoder model based on a multi-scale temporal convolutional network (MSTCN) and a convolutional neural network (CNN) to fully capture complex spatiotemporal features in normal flight data. Building on this foundation, memory network enhancement strategy models prototypes of spatiotemporal encoded features, adaptively extracting key memory features to gate residual injection into the decoder. This improves the model’s ability to stably represent normal patterns and mitigates excessive anomaly reconstruction caused by random noise. Concurrently, multi-view contrastive learning constrains the model to learn locally invariant representations under normal patterns, promoting compact clustering of normal samples and thereby improving the separability and discriminability of anomalies. Overall, under the federated learning framework, this paper adopts the federated averaging (FedAvg) algorithm to aggregate client model parameters for global collaborative optimization, thereby realizing distributed AD for UAV swarms while protecting local data privacy. Extensive experimental results on the ALFA dataset demonstrate that the proposed method significantly outperforms various representative methods in AD tasks.
- 11 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
One-shot Unsupervised Domain Adaptation for Semantic Segmentation with Self-Constrained Style Decoupling
One-shot unsupervised domain adaptation (OSUDA) aims to adapt a segmentation model from a labeled source domain to a target domain where only a single unlabeled datum is available. Although style transfer-based techniques, where the source images are stylized to have the appearance of the target domain, have shown impressive performance, they often suffer from a lack of content diversity, style distortion, or style overfitting. To mitigate these issues, we propose a novel Self-Constrained Style Decoupling (SCSD) framework to directly decouple the style of an image, extend the target style space, and leverage a text-to-image diffusion model to generate a synthetic target dataset with diverse photo-realistic images following the style of the target domain. Specifically, to realize OSUDA for semantic segmentation, SCSD carries out three learning stages, including a style decoupling stage, a self-constraining fine-tuning stage, and an adaptive segmentation stage. The style vector of the single target image is first decoupled by a style decoupling network in the style decoupling stage. Then, a fine-tuned text-to-image diffusion model with the style vectors of the target image’s patch-shuffled variants is deployed to generate style-diversified images aligned with the target style space. At the final adaptive segmentation stage, we integrate the source domain and generated target domain datasets to train the generalized UDA segmentation model. Our SCSD can be seamlessly integrated with any UDA segmentation models, underscoring the practical value. Extensive experiments on the Cityscapes, GTA, and SYNTHIA datasets show that our SCSD can achieve superior performance by outperforming state-of-the-art OSUDA and T2I personalization methods in the realistic synthetic source domain to real-world target domain adaptation task under the one-shot setting.
- 11 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
One-shot Unsupervised Domain Adaptation for Semantic Segmentation with Self-Constrained Style Decoupling
One-shot unsupervised domain adaptation (OSUDA) aims to adapt a segmentation model from a labeled source domain to a target domain where only a single unlabeled datum is available. Although style transfer-based techniques, where the source images are stylized to have the appearance of the target domain, have shown impressive performance, they often suffer from a lack of content diversity, style distortion, or style overfitting. To mitigate these issues, we propose a novel Self-Constrained Style Decoupling (SCSD) framework to directly decouple the style of an image, extend the target style space, and leverage a text-to-image diffusion model to generate a synthetic target dataset with diverse photo-realistic images following the style of the target domain. Specifically, to realize OSUDA for semantic segmentation, SCSD carries out three learning stages, including a style decoupling stage, a self-constraining fine-tuning stage, and an adaptive segmentation stage. The style vector of the single target image is first decoupled by a style decoupling network in the style decoupling stage. Then, a fine-tuned text-to-image diffusion model with the style vectors of the target image’s patch-shuffled variants is deployed to generate style-diversified images aligned with the target style space. At the final adaptive segmentation stage, we integrate the source domain and generated target domain datasets to train the generalized UDA segmentation model. Our SCSD can be seamlessly integrated with any UDA segmentation models, underscoring the practical value. Extensive experiments on the Cityscapes, GTA, and SYNTHIA datasets show that our SCSD can achieve superior performance by outperforming state-of-the-art OSUDA and T2I personalization methods in the realistic synthetic source domain to real-world target domain adaptation task under the one-shot setting.
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cognitive Communications and Networking
- Vol. 12, 9625-9640
Agentic GenAI-Enabled Resource Allocation for Low-Altitude Embodied Intelligence
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cognitive Communications and Networking
- Vol. 12, 9625-9640
Agentic GenAI-Enabled Resource Allocation for Low-Altitude Embodied Intelligence
- Open Access
- 8 November 2025
- Published by Springer Nature in European Spine Journal
- Vol. 35 (3) , 1238-1248
External validation of SpineNetv2 deep learning system for automated lumbar spine MRI analysis: A multi-pathology diagnostic agreement study
Background Magnetic resonance imaging (MRI) is the reference standard for evaluating degenerative lumbar spine disorders, but interpretation is time-consuming and subject to inter-observer variability. SpineNetv2, a publicly available deep learning system, enables automated analysis of multiple spinal pathologies. This study conducted an independent external validation of SpineNetv2 against expert reference assessments. Methods A total of 491 patients (2,455 lumbar discs, L1/2–L5/S1) were retrospectively included. Disc-level reference assessments were provided by an expert orthopedic surgeon, with a junior orthopedic surgeon serving as comparator. Six pathologies were assessed: disc degeneration (Pfirrmann grading), central canal stenosis (CCS), spondylolisthesis, herniation, and bilateral foraminal stenosis (FS). Performance metrics included sensitivity, specificity, positive predictive value, negative predictive value, F1-score, Matthews correlation coefficient, exact agreement, weighted kappa, and mean absolute error. McNemar’s test and bootstrap resampling (1,000 iterations) were used for statistical analysis. Results Overall agreement ranged from 83.5% to 97.5% (mean 92.8%). SpineNetv2 significantly outperformed the junior orthopedic surgeon in CCS, spondylolisthesis, and bilateral FS (all p ≤ 0.001), with comparable performance in herniation (p = 0.293). Pfirrmann grading showed lower MAE for SpineNetv2 compared with the junior surgeon (0.213 vs. 0.254, p = 0.001), though agreement declined in older patients and upper lumbar discs. Error analysis revealed a specificity-oriented profile, with false negatives exceeding false positives. Conclusions SpineNetv2 demonstrated high agreement across five binary lumbar pathologies, while Pfirrmann grading remained the main limitation, particularly in elderly upper lumbar discs. Its specificity-oriented profile supports use as a confirmatory second reader, but reliance on negative findings is not recommended. Broader reliability will require multicenter, multi-reader validation and sensitivity-oriented calibration.
- 8 November 2025
- Published by Springer Nature in European Spine Journal
- Vol. 35 (3) , 1238-1248
Open AccessExternal validation of SpineNetv2 deep learning system for automated lumbar spine MRI analysis: A multi-pathology diagnostic agreement study
Background Magnetic resonance imaging (MRI) is the reference standard for evaluating degenerative lumbar spine disorders, but interpretation is time-consuming and subject to inter-observer variability. SpineNetv2, a publicly available deep learning system, enables automated analysis of multiple spinal pathologies. This study conducted an independent external validation of SpineNetv2 against expert reference assessments. Methods A total of 491 patients (2,455 lumbar discs, L1/2–L5/S1) were retrospectively included. Disc-level reference assessments were provided by an expert orthopedic surgeon, with a junior orthopedic surgeon serving as comparator. Six pathologies were assessed: disc degeneration (Pfirrmann grading), central canal stenosis (CCS), spondylolisthesis, herniation, and bilateral foraminal stenosis (FS). Performance metrics included sensitivity, specificity, positive predictive value, negative predictive value, F1-score, Matthews correlation coefficient, exact agreement, weighted kappa, and mean absolute error. McNemar’s test and bootstrap resampling (1,000 iterations) were used for statistical analysis. Results Overall agreement ranged from 83.5% to 97.5% (mean 92.8%). SpineNetv2 significantly outperformed the junior orthopedic surgeon in CCS, spondylolisthesis, and bilateral FS (all p ≤ 0.001), with comparable performance in herniation (p = 0.293). Pfirrmann grading showed lower MAE for SpineNetv2 compared with the junior surgeon (0.213 vs. 0.254, p = 0.001), though agreement declined in older patients and upper lumbar discs. Error analysis revealed a specificity-oriented profile, with false negatives exceeding false positives. Conclusions SpineNetv2 demonstrated high agreement across five binary lumbar pathologies, while Pfirrmann grading remained the main limitation, particularly in elderly upper lumbar discs. Its specificity-oriented profile supports use as a confirmatory second reader, but reliance on negative findings is not recommended. Broader reliability will require multicenter, multi-reader validation and sensitivity-oriented calibration.
- 6 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cognitive Communications and Networking
- Vol. 12, 3250-3264
Diffusion-Based Trajectory Optimization and Resource Allocation for Hybrid Aircraft in Low-Altitude Economy Networks
Relying on low-altitude airspace and emerging communication technologies, the low-altitude economy plays a dominant role in the general aviation domain. Robust and efficient low-altitude economy networks with hybrid aircraft are indispensable for supporting complex and large-scale operations of low-altitude economy. However, hybrid aircraft features dynamic spatial structures and diverse task requirements. In this work, we propose a low-altitude economy network framework to support the robust and efficient operations of heterogeneous unmanned aerial vehicles (UAVs) and electric vertical take-off and landing vehicles (eVTOLs). To ensure reliable flights, a secure distance between two aircraft is defined. In the proposed network framework, we formulate a long-term network energy optimization problem for trajectory generation and resource allocation of hybrid aircraft, subject to the constraints of secure distances and task queue stability. Then, the initial time-average energy optimization problem is transformed into deterministic sub-problems across different time slots by Lyapunov optimization. Based on the auxiliary gradients provided by the deterministic sub-problems, a novel diffusion-based trajectory generation (DTG) algorithm is proposed to generate the optimal trajectories of hybrid aircraft with guided sampling, where secure distances act as penalties for trajectory generation. Finally, the effectiveness of the proposed DTG algorithm is evaluated through both theoretical analysis and simulation experiments by comparing it with benchmark policies.
- 6 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cognitive Communications and Networking
- Vol. 12, 3250-3264
Diffusion-Based Trajectory Optimization and Resource Allocation for Hybrid Aircraft in Low-Altitude Economy Networks
Relying on low-altitude airspace and emerging communication technologies, the low-altitude economy plays a dominant role in the general aviation domain. Robust and efficient low-altitude economy networks with hybrid aircraft are indispensable for supporting complex and large-scale operations of low-altitude economy. However, hybrid aircraft features dynamic spatial structures and diverse task requirements. In this work, we propose a low-altitude economy network framework to support the robust and efficient operations of heterogeneous unmanned aerial vehicles (UAVs) and electric vertical take-off and landing vehicles (eVTOLs). To ensure reliable flights, a secure distance between two aircraft is defined. In the proposed network framework, we formulate a long-term network energy optimization problem for trajectory generation and resource allocation of hybrid aircraft, subject to the constraints of secure distances and task queue stability. Then, the initial time-average energy optimization problem is transformed into deterministic sub-problems across different time slots by Lyapunov optimization. Based on the auxiliary gradients provided by the deterministic sub-problems, a novel diffusion-based trajectory generation (DTG) algorithm is proposed to generate the optimal trajectories of hybrid aircraft with guided sampling, where secure distances act as penalties for trajectory generation. Finally, the effectiveness of the proposed DTG algorithm is evaluated through both theoretical analysis and simulation experiments by comparing it with benchmark policies.