# Rethinking Motion Representation: Residual Frames with 3D ConvNets for Better Action Recognition

Source: [Rethinking Motion Representation: Residual Frames with 3D ConvNets for Better Action Recognition](<https://www.sota2.com/research/paper/68fa66ed1e209131cea13465>)

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

Data updated: 2025-10-25T22:02:19.923Z

Authors: Li Tao, Xueting Wang, Toshihiko Yamasaki

Published: 2020-01-16T05:49:13.000Z

## Abstract

Recently, 3D convolutional networks yield good performance in action recognition. However, optical flow stream is still needed to ensure better performance, the cost of which is very high. In this paper, we propose a fast but effective way to extract motion features from videos utilizing residual frames as the input data in 3D ConvNets. By replacing traditional stacked RGB frames with residual ones, 20.5% and 12.5% points improvements over top-1 accuracy can be achieved on the UCF101 and HMDB51 datasets when trained from scratch. Because residual frames contain little information of object appearance, we further use a 2D convolutional network to extract appearance features and combine them with the results from residual frames to form a two-path solution. In three benchmark datasets, our two-path solution achieved better or comparable performances than those using additional optical flow methods, especially outperformed the state-of-the-art models on Mini-kinetics dataset. Further analysis indicates that better motion features can be extracted using residual frames with 3D ConvNets, and our residual-frame-input path is a good supplement for existing RGB-frame-input models.

## 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/2001.05661>)

[PDF](<https://arxiv.org/pdf/2001.05661.pdf>)
