Challenge report:VIPriors Action Recognition Challenge

by   Zhipeng Luo, et al.

This paper is a brief report to our submission to the VIPriors Action Recognition Challenge. Action recognition has attracted many researchers attention for its full application, but it is still challenging. In this paper, we study previous methods and propose our method. In our method, we are primarily making improvements on the SlowFast Network and fusing with TSM to make further breakthroughs. Also, we use a fast but effective way to extract motion features from videos by using residual frames as input. Better motion features can be extracted using residual frames with SlowFast, and the residual-frame-input path is an excellent supplement for existing RGB-frame-input models. And better performance obtained by combining 3D convolution(SlowFast) with 2D convolution(TSM). The above experiments were all trained from scratch on UCF101.



There are no comments yet.


page 1

page 2

page 3

page 4


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

Recently, 3D convolutional networks yield good performance in action rec...

Motion Representation Using Residual Frames with 3D CNN

Recently, 3D convolutional networks (3D ConvNets) yield good performance...

Residual Frames with Efficient Pseudo-3D CNN for Human Action Recognition

Human action recognition is regarded as a key cornerstone in domains suc...

SMART Frame Selection for Action Recognition

Action recognition is computationally expensive. In this paper, we addre...

Learn to cycle: Time-consistent feature discovery for action recognition

Temporal motion has been one of the essential components for effectively...

Challenge report: Recognizing Families In the Wild Data Challenge

This paper is a brief report to our submission to the Recognizing Famili...

MGSampler: An Explainable Sampling Strategy for Video Action Recognition

Frame sampling is a fundamental problem in video action recognition due ...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.