Kun Yang

Kun Yang

Auto-generated profile, based on publicly available information

Kun Yang

Academy for Engineering and Technology, Fudan University, Shanghai, China

Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

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

Representative Publications

View All Publications
2 August 2023 in IEEE Transactions on Industrial Informatics
Verified
Journal Article
Closed access
YLYang Liu
Yang Liu
JLJing Liu
Jing Liu
KYKun Yang
Kun Yang
BJBobo Ju
Bobo Ju
SLSiao Liu
Siao Liu
Liang SongLiang Song
Liang Song
As essential tools for industry safety protection, automatic video anomaly detection systems (AVADS) are designed to detect anomalous events of concern in surveillance videos. Existing VAD methods lack effective exploration of the prototypical appearance and motion features leading to poor performance in realistic scenarios. Specifically, they either misreport regular events as anomalies due to insufficient representation power, or lead to missed detections with over-power generalization. In this regard, we propose an appearance-motion prototype network (AMP-net) that uses external memories to record prototype features and augments the appearance-motion prototype with a spatial-temporal fusion. In addition, AMP-net sequentially fuses appearance features from deep to shallow to utilize multiscale spatial context. Additionally, we introduce temporal attention to capture important dynamics and enhance AMP-net for representing regular motion. The proposed method achieves a delicate balance of effective representation of normal events and limited generalization to anomalies. Experiments on three benchmark datasets demonstrate that our method can accurately detect anomalous events, achieving performance comparable to state-of-the-art methods with frame-level AUCs of 98.7%, 92.4%, and 78.8% on the UCSD Ped2, CUHK Avenue, and ShanghaiTech datasets. Moreover, we conducted a case study on the self-collected industrial dataset, and the results indicate that our AMP-net can cope with complex industrial scenarios and outperform existing methods.

2 March 2026 in IEEE Communications Surveys & Tutorials
Verified
Journal Article
Closed access
JLJing Liu
Jing Liu
Yao DuYao Du
Yao Du
KYKun Yang
Kun Yang
JWJiaqi Wu
Jiaqi Wu
YWYan Wang
Yan Wang
Victor C. M. LeungVictor C. M. Leung
Victor C. M. Leung
Edge-cloud collaborative computing (ECCC) has emerged as a pivotal paradigm for addressing the computational demands of modern intelligent applications, integrating cloud resources with edge devices to enable efficient, low-latency processing across distributed communication networks. Recent advancements in AI, particularly deep learning and large language models (LLMs), have dramatically enhanced the capabilities of these networked systems, yet introduce significant challenges in model deployment, network resource management, and cross-layer optimization. In this survey, we comprehensively examine the intersection of distributed intelligence and model optimization within edge-cloud environments, providing a structured tutorial on fundamental architectures, communication protocols, and network-aware computing frameworks. Additionally, we systematically analyze model optimization approaches, including compression, adaptation, and neural architecture search, alongside AI-driven resource management strategies that balance performance, energy efficiency, and communication overhead across heterogeneous networks. We further explore critical aspects of privacy protection and security enhancement within ECCC systems and examine practical deployments through diverse networked applications, spanning autonomous driving, healthcare, and industrial automation. Performance analysis and benchmarking techniques are also thoroughly explored to establish evaluation standards for these complex distributed systems. Furthermore, the review identifies critical research directions including LLMs deployment, 6G integration, neuromorphic computing, and quantum computing, offering a roadmap for addressing persistent challenges in heterogeneity management, real-time processing, and scalability. By bridging theoretical advancements in communications with practical deployments, this survey offers researchers and practitioners a holistic perspective on leveraging AI to optimize distributed computing environments over next-generation communication networks, fostering innovation in intelligent networked systems.

26 October 2023
Verified
Conference Paper
Open access
KYKun Yang
Kun Yang
DYDingkang Yang
Dingkang Yang
JZJingyu Zhang
Jingyu Zhang
HWHanqi Wang
Hanqi Wang
PSPeng Sun
Peng Sun
Liang SongLiang Song
Liang Song
Multi-agent collaborative perception has received increasing attention recently as an emerging application in driving scenarios. Despite advancements in previous approaches, challenges remain due to redundant communication patterns and vulnerable collaboration processes. To address these issues, we propose What2comm, an end-to-end collaborative perception framework to achieve a trade-off between perception performance and communication bandwidth. Our novelties lie in three aspects. First, we design an efficient communication mechanism based on feature decoupling to transmit exclusive and common feature maps among heterogeneous agents to provide perceptually holistic messages. Secondly, a spatio-temporal collaboration module is introduced to integrate complementary information from collaborators and temporal ego cues, leading to a robust collaboration procedure against transmission delay and localization errors. Ultimately, we propose a common-aware fusion strategy to refine final representations with informative common features. Comprehensive experiments in real-world and simulated scenarios demonstrate the effectiveness of What2comm.

13 August 2024 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
DYDingkang Yang
Dingkang Yang
KYKun Yang
Kun Yang
HKHaopeng Kuang
Haopeng Kuang
ZCZhaoyu Chen
Zhaoyu Chen
YWYuzheng Wang
Yuzheng Wang
LZLihua Zhang
Lihua Zhang
Understanding emotions from diverse contexts has received widespread attention in computer vision communities. The core philosophy of Context-Aware Emotion Recognition (CAER) is to provide valuable semantic cues for recognizing the emotions of target persons by leveraging rich contextual information. Current approaches invariably focus on designing sophisticated structures to extract perceptually critical representations from contexts. Nevertheless, a long-neglected dilemma is that a severe context bias in existing datasets results in an unbalanced distribution of emotional states among different contexts, causing biased visual representation learning. From a causal demystification perspective, the harmful bias is identified as a confounder that misleads existing models to learn spurious correlations based on likelihood estimation, limiting the models’ performance. To address the issue, we embrace causal inference to disentangle the models from the impact of such bias, and formulate the causalities among variables in the CAER task via a customized causal graph. Subsequently, we present a Contextual Causal Intervention Module (CCIM) to de-confound the confounder, which is built upon backdoor adjustment theory to facilitate seeking approximate causal effects during model training. As a plug-and-play component, CCIM can easily integrate with existing approaches and bring significant improvements. Systematic experiments on three datasets demonstrate the effectiveness of our CCIM.

5 June 2024 in IEEE Transactions on Vehicular Technology
Verified
Journal Article
Closed access
JZJingyu Zhang
Jingyu Zhang
KYKun Yang
Kun Yang
HWHanqi Wang
Hanqi Wang
PSPeng Sun
Peng Sun
Liang SongLiang Song
Liang Song
In collaborative perception, autonomous vehicles with limited perception capabilities can communicate with each other to achieve a more holographic and effective perception result. Real-world communication systems, however, are usually constrained by wireless communication resources or reliability and cannot handle the enormous real-time data transmissions to support the delay-sensitive collaborative perception. To resolve this issue, we propose an efficient vehicular Collaborative Perception method based on Spatial-temporal feature Compression (CPSC) that exploits the trade-off between perception performance and bandwidth consumption. It performs feature-level compression by focusing on critical regions of perceptual information in the spatial-temporal domain and adapts traffic according to network conditions. To the best of our knowledge, this paper presents the first work where temporal feature redundancy is considered for enhancing the efficiency of collaborative perception. To thoroughly evaluate CPSC, we conduct extensive experiments of collaborative 3D object detection tasks on the real-world dataset DAIR-V2X and the simulated dataset OPV2V. The results show that CPSC outperforms the SOTA collaborative perception methods by 2.91% for AP@0.7 in OPV2V dataset and 1.71% for AP@0.5 in DAIR-V2X dataset. Meanwhile, CPSC attains a communication volume reduction of more than 10 times while consistently outperforming the previous SOTA method.

29 July 2024 in IEEE Transactions on Circuits and Systems for Video Technology
Verified
Journal Article
Closed access
DYDingkang Yang
Dingkang Yang
MLMingcheng Li
Mingcheng Li
LQLinhao Qu
Linhao Qu
KYKun Yang
Kun Yang
PZPeng Zhai
Peng Zhai
LZLihua Zhang
Lihua Zhang
Understanding human intentions ( e.g ., emotions) from videos has received considerable attention recently. Video streams generally constitute a blend of temporal data stemming from distinct modalities, including natural language, facial expressions, and auditory clues. Despite the impressive advancements of previous works via attention-based paradigms, the inherent temporal asynchrony and modality heterogeneity challenges remain in multimodal sequence fusion, causing adverse performance bottlenecks. To tackle these issues, we propose a Multimodal fusion approach for learning modality-Exclusive and modality-Agnostic representations (MEA) to refine multimodal features and leverage the complementarity across distinct modalities. On the one hand, MEA introduces a predictive self-attention module to capture reliable context dynamics within modalities and reinforce unique features over the modality-exclusive spaces. On the other hand, a hierarchical cross-modal attention module is designed to explore valuable element correlations among modalities over the modality-agnostic space. Meanwhile, a double-discriminator strategy is presented to ensure the production of distinct representations in an adversarial manner. Eventually, we propose a decoupled graph fusion mechanism to enhance knowledge exchange across heterogeneous modalities and learn robust multimodal representations for downstream tasks. Numerous experiments are implemented on three multimodal datasets with asynchronous sequences. Systematic analyses show the necessity of our approach.