mlsanityData to 14 Oct 2026

A Survey on Efficiency Optimization Techniques for DNN-based Video Analytics: Process Systems, Algorithms, and Applications

arXiv 2507.15628 ↗First posted 21 Jul 2025cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

The explosive growth of video data in recent years has brought higher demands for video analytics, where accuracy and efficiency remain the two primary concerns. Deep neural networks (DNNs) have been widely adopted to ensure accuracy; however, improving their efficiency in video analytics remains an open challenge. Different from existing surveys that make summaries of DNN-based video mainly from the accuracy optimization aspect, in this survey, we aim to provide a thorough review of optimization techniques focusing on the improvement of the efficiency of DNNs in video analytics. We organize existing methods in a bottom-up manner, covering multiple perspectives such as hardware support, data processing, operational deployment, etc. Finally, based on the optimization framework and existing works, we analyze and discuss the problems and challenges in the performance optimization of DNN-based video analytics.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 52 of its 143 references that are in the map. First posted on arXiv 21 Jul 2025.

Builds on

52 of 143 references.

References · 52

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  3. 2021On the Opportunities and Risks of Foundation Modelscited by 4,033
  4. 2015Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Codingcited by 2,329
  5. 2017Non-local Neural Networkscited by 2,293
  6. 2023VideoMAE V2: Scaling Video Masked Autoencoders with Dual Maskingcited by 528
  7. 2022InternVideo: General Video Foundation Models via Generative and Discriminative Learningcited by 447
  8. 2023A Comprehensive Survey on Pretrained Foundation Models: A History from BERT to ChatGPTcited by 368
  9. 2018Human Action Recognition and Prediction: A Surveycited by 227
  10. 2023Unmasked Teacher: Towards Training-Efficient Video Foundation Modelscited by 199
  11. 2022OmniVL:One Foundation Model for Image-Language and Video-Language Taskscited by 143
  12. 2018AdaFrame: Adaptive Frame Selection for Fast Video Recognitioncited by 134
38 more
  1. 2019SCSampler: Sampling Salient Clips from Video for Efficient Action Recognitioncited by 134
  2. 2019Pixel-Adaptive Convolutional Neural Networkscited by 126
  3. 2020A Review on Deep Learning Techniques for Video Predictioncited by 114
  4. 2020AR-Net: Adaptive Frame Resolution for Efficient Action Recognitioncited by 88
  5. 2021Adaptive Focus for Efficient Video Recognitioncited by 77
  6. 2019Efficient Video Super-Resolution through Recurrent Latent Space Propagationcited by 69
  7. 2018NestDNN: Resource-Aware Multi-Tenant On-Device Deep Learning for Continuous Mobile Visioncited by 68
  8. 2019Multi-Agent Reinforcement Learning Based Frame Sampling for Effective Untrimmed Video Recognitioncited by 66
  9. 2018Online Model Distillation for Efficient Video Inferencecited by 60
  10. 2021FrameExit: Conditional Early Exiting for Efficient Video Recognitioncited by 59
  11. 2017Video Salient Object Detection via Fully Convolutional Networkscited by 46
  12. 2020Revisiting Temporal Modeling for Video Super-resolutioncited by 46
  13. 2021Temporal RoI Align for Video Object Recognitioncited by 44
  14. 2018BlazeIt: Optimizing Declarative Aggregation and Limit Queries for Neural Network-Based Video Analyticscited by 41
  15. 2020Distilled Semantics for Comprehensive Scene Understanding from Videoscited by 39
  16. 2019Scaling Video Analytics on Constrained Edge Nodescited by 36
  17. 2021Dynamic Network Quantization for Efficient Video Inferencecited by 36
  18. 2021Skip-Convolutions for Efficient Video Processingcited by 32
  19. 2019Progressive Sparse Local Attention for Video object detectioncited by 30
  20. 2017A Survey on Content-Aware Video Analysis for Sportscited by 27
  21. 2019AdaScale: Towards Real-time Video Object Detection Using Adaptive Scalingcited by 27
  22. 2020Dynamic Inference: A New Approach Toward Efficient Video Action Recognitioncited by 25
  23. 2022OCSampler: Compressing Videos to One Clip with Single-step Samplingcited by 23
  24. 2019Looking Fast and Slow: Memory-Guided Mobile Video Object Detectioncited by 22
  25. 2022Look Back and Forth: Video Super-Resolution with Explicit Temporal Difference Modelingcited by 20
  26. 2023MobileVOS: Real-Time Video Object Segmentation Contrastive Learning meets Knowledge Distillationcited by 16
  27. 2020ApproxDet: Content and Contention-Aware Approximate Object Detection for Mobilescited by 15
  28. 2019Rekall: Specifying Video Events using Compositions of Spatiotemporal Labelscited by 14
  29. 2019Patchwork: A Patch-wise Attention Network for Efficient Object Detection and Segmentation in Video Streamscited by 13
  30. 2018VStore: A Data Store for Analytics on Large Videoscited by 9
  31. 2021A Serverless Cloud-Fog Platform for DNN-Based Video Analytics with Incremental Learningcited by 9
  32. 2018An Energy-Efficient FPGA-based Deconvolutional Neural Networks Accelerator for Single Image Super-Resolutioncited by 8
  33. 2020TASM: A Tile-Based Storage Manager for Video Analyticscited by 7
  34. 2022AccMPEG: Optimizing Video Encoding for Video Analyticscited by 7
  35. 2020Hysia: Serving DNN-Based Video-to-Retail Applications in Cloudcited by 5
  36. 2021PatchNet -- Short-range Template Matching for Efficient Video Processingcited by 5
  37. 2021VSS: A Storage System for Video Analytics [Technical Report]cited by 5
  38. 2018Inference of Quantized Neural Networks on Heterogeneous All-Programmable Devicescited by 4

50 most cited of 52 All 52 (JSON)

Built on by

Not cited yet.