A Survey on Video Analytics in Cloud-Edge-Terminal Collaborative Systems
Not on the map. Why?
Abstract (arXiv)
The explosive growth of video data has driven the development of distributed video analytics in cloud-edge-terminal collaborative (CETC) systems, enabling efficient video processing, real-time inference, and privacy-preserving analysis. Among multiple advantages, CETC systems can distribute video processing tasks and enable adaptive analytics across cloud, edge, and terminal devices, leading to breakthroughs in video surveillance, autonomous driving, and smart cities. In this survey, we first analyze fundamental architectural components, including hierarchical, distributed, and hybrid frameworks, alongside edge computing platforms and resource management mechanisms. Building upon these foundations, edge-centric approaches emphasize on-device processing, edge-assisted offloading, and edge intelligence, while cloud-centric methods leverage powerful computational capabilities for complex video understanding and model training. Our investigation also covers hybrid video analytics incorporating adaptive task offloading and resource-aware scheduling techniques that optimize performance across the entire system. Beyond conventional approaches, recent advances in large language models and multimodal integration reveal both opportunities and challenges in platform scalability, data protection, and system reliability. Future directions also encompass explainable systems, efficient processing mechanisms, and advanced video analytics, offering valuable insights for researchers and practitioners in this dynamic field.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 44 of its 57 references that are in the map. First posted on arXiv 10 Feb 2025.
Builds on
44 of 57 references.
References · 44
- 2023Video-Bench: A Comprehensive Benchmark and Toolkit for Evaluating Video-based Large Language Modelscited by 107
- 2024Video-LaVIT: Unified Video-Language Pre-training with Decoupled Visual-Motional Tokenizationcited by 100
- 2023Unleashing the Power of Edge-Cloud Generative AI in Mobile Networks: A Survey of AIGC Servicescited by 76
- 2023Generalized Video Anomaly Event Detection: Systematic Taxonomy and Comparison of Deep Modelscited by 59
- 2020Ekya: Continuous Learning of Video Analytics Models on Edge Compute Serverscited by 58
- 2018End-to-End Learning of Motion Representation for Video Understandingcited by 43
- 2023TransFlow: Transformer as Flow Learnercited by 32
- 2022Towards Open Set Video Anomaly Detectioncited by 26
- 2022DyAnNet: A Scene Dynamicity Guided Self-Trained Video Anomaly Detection Networkcited by 26
- 2022Unsupervised Anomaly Localization with Structural Feature-Autoencoderscited by 23
- 2020Symbolic Pregression: Discovering Physical Laws from Distorted Videocited by 21
- 2018Massively Parallel Video Networkscited by 16
32 more
- 2021Llama: A Heterogeneous & Serverless Framework for Auto-Tuning Video Analytics Pipelinescited by 16
- 2019CROSSBOW: Scaling Deep Learning with Small Batch Sizes on Multi-GPU Serverscited by 14
- 2019REVAMP2T: Real-time Edge Video Analytics for Multi-camera Privacy-aware Pedestrian Trackingcited by 14
- 2022Fed-FSNet: Mitigating Non-I.I.D. Federated Learning via Fuzzy Synthesizing Networkcited by 14
- 2022iGniter: Interference-Aware GPU Resource Provisioning for Predictable DNN Inference in the Cloudcited by 14
- 2023Variance-Covariance Regularization Improves Representation Learningcited by 14
- 2023Shoggoth: Towards Efficient Edge-Cloud Collaborative Real-Time Video Inference via Adaptive Online Learningcited by 11
- 2020Video Anomaly Detection by Estimating Likelihood of Representationscited by 9
- 2021A Serverless Cloud-Fog Platform for DNN-Based Video Analytics with Incremental Learningcited by 9
- 2023Equilibrium in the Computing Continuum through Active Inferencecited by 9
- 2022Beyond Transfer Learning: Co-finetuning for Action Localisationcited by 8
- 2023Ego-Vehicle Action Recognition based on Semi-Supervised Contrastive Learningcited by 8
- 2022Turbo: Opportunistic Enhancement for Edge Video Analyticscited by 7
- 2020Automatic Pruning for Quantized Neural Networkscited by 6
- 2021Single-path Bit Sharing for Automatic Loss-aware Model Compressioncited by 6
- 2021perf4sight: A toolflow to model CNN training performance on Edge GPUscited by 4
- 2022Sustainable AI Processing at the Edgecited by 4
- 2022Hyperspherical Quantization: Toward Smaller and More Accurate Modelscited by 4
- 2024HierSFL: Local Differential Privacy-aided Split Federated Learning in Mobile Edge Computingcited by 3
- 2018Real-Time Index Authentication for Event-Oriented Surveillance Video Query using Blockchaincited by 2
- 2019Hyper: Distributed Cloud Processing for Large-Scale Deep Learning Taskscited by 2
- 2020Descriptive and Predictive Analysis of Aggregating Functions in Serverless Clouds: the Case of Video Streamingcited by 2
- 2021Energy-Aware Adaptive Offloading of Soft Real-Time Jobs in Mobile Edge Cloudscited by 2
- 2022Efficient Heterogeneous Video Segmentation at the Edgecited by 2
- 2022EdgeVision: Towards Collaborative Video Analytics on Distributed Edges for Performance Maximizationcited by 2
- 2023Towards Compute-Optimal Transfer Learningcited by 2
- 2024SAMEdge: An Edge-cloud Video Analytics Architecture for the Segment Anything Modelcited by 2
- 2018A Robust Background Initialization Algorithm with Superpixel Motion Detectioncited by 1
- 2019DeGraF-Flow: Extending DeGraF Features for accurate and efficient sparse-to-dense optical flow estimationcited by 1
- 2020EdgeDASH: Exploiting Network-Assisted Adaptive Video Streaming for Edge Cachingcited by 1
- 2020Denoising-based Turbo Message Passing for Compressed Video Background Subtractioncited by 1
- 2024Deep-learning Optical Flow Outperforms PIV in Obtaining Velocity Fields from Active Nematicscited by 1
Built on by
Citing papers per year: 2025: 1; 2026: 1.
2 papers.