mlsanityData to 14 Oct 2026

Event Neural Networks

arXiv 2112.00891 ↗First posted 2 Dec 2021cs.CVcited by 5

Not on the map. Why?

Abstract (arXiv)

Video data is often repetitive; for example, the contents of adjacent frames are usually strongly correlated. Such redundancy occurs at multiple levels of complexity, from low-level pixel values to textures and high-level semantics. We propose Event Neural Networks (EvNets), which leverage this redundancy to achieve considerable computation savings during video inference. A defining characteristic of EvNets is that each neuron has state variables that provide it with long-term memory, which allows low-cost, high-accuracy inference even in the presence of significant camera motion. We show that it is possible to transform a wide range of neural networks into EvNets without re-training. We demonstrate our method on state-of-the-art architectures for both high- and low-level visual processing, including pose recognition, object detection, optical flow, and image enhancement. We observe roughly an order-of-magnitude reduction in computational costs compared to conventional networks, with minimal reductions in model accuracy.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 47 of its 71 references that are in the map. First posted on arXiv 2 Dec 2021.

Builds on

47 of 71 references.

References · 47

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  2. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  3. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,852
  4. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,845
  5. 2015SSD: Single Shot MultiBox Detectorcited by 3,130
  6. 2015Learning both Weights and Connections for Efficient Neural Networkscited by 2,031
  7. 2018SlowFast Networks for Video Recognitioncited by 1,867
  8. 2019Deep High-Resolution Representation Learning for Human Pose Estimationcited by 1,339
  9. 2017ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devicescited by 1,200
  10. 2016Pruning Filters for Efficient ConvNetscited by 1,143
  11. 2016Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,064
  12. 2016SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model sizecited by 1,060
35 more
  1. 2016Deep Networks with Stochastic Depthcited by 979
  2. 2017PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volumecited by 968
  3. 2016XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networkscited by 849
  4. 2017Focal Loss for Dense Object Detectioncited by 752
  5. 2017BranchyNet: Fast Inference via Early Exiting from Deep Neural Networkscited by 596
  6. 2015BinaryConnect: Training Deep Neural Networks with binary weights during propagationscited by 592
  7. 2018Simple Baselines for Human Pose Estimation and Trackingcited by 502
  8. 2017Deep Bilateral Learning for Real-Time Image Enhancementcited by 200
  9. 2017BlockDrop: Dynamic Inference Paths in Residual Networkscited by 189
  10. 2016Deep Feature Flow for Video Recognitioncited by 186
  11. 2017Convolutional Networks with Adaptive Inference Graphscited by 148
  12. 2020Resolution Adaptive Networks for Efficient Inferencecited by 146
  13. 2018AdaFrame: Adaptive Frame Selection for Fast Video Recognitioncited by 134
  14. 2020Memory Enhanced Global-Local Aggregation for Video Object Detectioncited by 128
  15. 2017Compressed Video Action Recognitioncited by 106
  16. 2020Event-based Asynchronous Sparse Convolutional Networkscited by 104
  17. 2020AR-Net: Adaptive Frame Resolution for Efficient Action Recognitioncited by 88
  18. 2018Accel: A Corrective Fusion Network for Efficient Semantic Segmentation on Videocited by 78
  19. 2019LiteEval: A Coarse-to-Fine Framework for Resource Efficient Video Recognitioncited by 65
  20. 2018Low-Latency Video Semantic Segmentationcited by 61
  21. 2017Towards High Performance Video Object Detectioncited by 60
  22. 2021FrameExit: Conditional Early Exiting for Efficient Video Recognitioncited by 59
  23. 2018Asynchronous Convolutional Networks for Object Detection in Neuromorphic Camerascited by 57
  24. 2016Clockwork Convnets for Video Semantic Segmentationcited by 55
  25. 2017Skip RNN: Learning to Skip State Updates in Recurrent Neural Networkscited by 49
  26. 2021AdaFuse: Adaptive Temporal Fusion Network for Efficient Action Recognitioncited by 48
  27. 2021Skip-Convolutions for Efficient Video Processingcited by 32
  28. 2019Dynamic Kernel Distillation for Efficient Pose Estimation in Videoscited by 30
  29. 2019AdaScale: Towards Real-time Video Object Detection Using Adaptive Scalingcited by 27
  30. 2019Asynchronous Single-Photon 3D Imagingcited by 25
  31. 2016Delta Networks for Optimized Recurrent Network Computationcited by 18
  32. 2020Robust and efficient post-processing for video object detectioncited by 16
  33. 2020ApproxDet: Content and Contention-Aware Approximate Object Detection for Mobilescited by 15
  34. 2016Sigma Delta Quantized Networkscited by 13
  35. 2018Recurrent Residual Module for Fast Inference in Videoscited by 13

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 1; 2023: 2; 2024: 0; 2025: 1; 2026: 1.

5 papers.

  1. 2023Eventful Transformers: Leveraging Temporal Redundancy in Vision Transformerscited by 13
  2. 2022MotionDeltaCNN: Sparse CNN Inference of Frame Differences in Moving Camera Videoscited by 5
  3. 2023ResQ: Residual Quantization for Video Perceptioncited by 2
  4. 2025ReFrame: Layer Caching for Accelerated Inference in Real-Time Renderingcited by 0
  5. 2026Efficient Tracking and Understanding Object Transformationscited by 0