# Recurrent Residual Module for Fast Inference in Videos

Source: [Recurrent Residual Module for Fast Inference in Videos](<https://www.sota2.com/research/paper/68fa64151e209131cea02ab9>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T20:56:11.088Z

Authors: Bowen Pan, Wuwei Lin, Xiaolin Fang, Chaoqin Huang, Bolei Zhou, Cewu Lu

Published: 2018-02-27T05:25:20.000Z

## Abstract

Deep convolutional neural networks (CNNs) have made impressive progress in many video recognition tasks such as video pose estimation and video object detection. However, CNN inference on video is computationally expensive due to processing dense frames individually. In this work, we propose a framework called Recurrent Residual Module (RRM) to accelerate the CNN inference for video recognition tasks. This framework has a novel design of using the similarity of the intermediate feature maps of two consecutive frames, to largely reduce the redundant computation. One unique property of the proposed method compared to previous work is that feature maps of each frame are precisely computed. The experiments show that, while maintaining the similar recognition performance, our RRM yields averagely 2x acceleration on the commonly used CNNs such as AlexNet, ResNet, deep compression model (thus 8-12x faster than the original dense models using the efficient inference engine), and impressively 9x acceleration on some binary networks such as XNOR-Nets (thus 500x faster than the original model). We further verify the effectiveness of the RRM on speeding up CNNs for video pose estimation and video object detection.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1802.09723>)

[PDF](<https://arxiv.org/pdf/1802.09723.pdf>)
