# EVA2: Exploiting Temporal Redundancy in Live Computer Vision

arXiv: https://arxiv.org/abs/1803.06312 · HTML: https://mlsanity.com/paper/1803.06312/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Mar 2018.

## Built on by (most cited first, 13 of 13)

- [Neighbourhood Representative Sampling for Efficient End-to-end Video Quality Assessment](https://mlsanity.com/paper/2210.05357/) (2022)
- [An LMM for Efficient Video Understanding via Reinforced Compression of Video Cubes](https://mlsanity.com/paper/2504.15270/) (2025)
- [Boosting Mobile CNN Inference through Semantic Memory](https://mlsanity.com/paper/2112.02644/) (2021)
- [D'ej`a Vu: Efficient Video-Language Query Engine with Learning-based Inter-Frame Computation Reuse](https://mlsanity.com/paper/2506.14107/) (2025)
- [Neo: Real-Time On-Device 3D Gaussian Splatting with Reuse-and-Update Sorting Acceleration](https://mlsanity.com/paper/2511.12930/) (2025)
- [Real-Time Robust Video Object Detection System Against Physical-World Adversarial Attacks](https://mlsanity.com/paper/2208.09195/) (2022)
- [Training for temporal sparsity in deep neural networks, application in video processing](https://mlsanity.com/paper/2107.07305/) (2021)
- [Drastically Reducing the Number of Trainable Parameters in Deep CNNs by Inter-layer Kernel-sharing](https://mlsanity.com/paper/2210.14151/) (2022)
- [Characterizing and Taming Resolution in Convolutional Neural Networks](https://mlsanity.com/paper/2110.14819/) (2021)
- [Treasure What You Have: Exploiting Similarity in Deep Neural Networks for Efficient Video Processing](https://mlsanity.com/paper/2305.06492/) (2023)
- [Kaleido: Algorithm-Hardware Co-Design for Video Diffusion Transformers by Exploiting Latent Space Correlations](https://mlsanity.com/paper/2607.13770/) (2026)
- [Deltoris: Enabling Real-time VLA Inference in Embodied AI via Bit-level Sparsity and Speculative Inference](https://mlsanity.com/paper/2608.04428/) (2026)
- [Algorithm-Architecture Co-Design for Efficient VLA Inference via Speculative Inference and Verification](https://mlsanity.com/paper/2608.15636/) (2026)

## Abstract (arXiv)

Hardware support for deep convolutional neural networks (CNNs) is critical to advanced computer vision in mobile and embedded devices. Current designs, however, accelerate generic CNNs; they do not exploit the unique characteristics of real-time vision. We propose to use the temporal redundancy in natural video to avoid unnecessary computation on most frames. A new algorithm, activation motion compensation, detects changes in the visual input and incrementally updates a previously-computed output. The technique takes inspiration from video compression and applies well-known motion estimation techniques to adapt to visual changes. We use an adaptive key frame rate to control the trade-off between efficiency and vision quality as the input changes. We implement the technique in hardware as an extension to existing state-of-the-art CNN accelerator designs. The new unit reduces the average energy per frame by 54.2%, 61.7%, and 87.6% for three CNNs with less than 1% loss in vision accuracy.