Motion Feature Network: Fixed Motion Filter for Action Recognition

07/26/2018
by   Seungeui Lee, et al.
0

Spatio-temporal representations in frame sequences play an important role in the task of action recognition. Previously, a method of using optical flow as a temporal information in combination with a set of RGB images that contain spatial information has shown great performance enhancement in the action recognition tasks. However, it has an expensive computational cost and requires two-stream (RGB and optical flow) framework. In this paper, we propose MFNet (Motion Feature Network) containing motion blocks which make it possible to encode spatio-temporal information between adjacent frames in a unified network that can be trained end-to-end. The motion block can be attached to any existing CNN-based action recognition frameworks with only a small additional cost. We evaluated our network on two of the action recognition datasets (Jester and Something-Something) and achieved competitive performances for both datasets by training the networks from scratch.

READ FULL TEXT
research
11/29/2017

Optical Flow Guided Feature: A Fast and Robust Motion Representation for Video Action Recognition

Motion representation plays a vital role in human action recognition in ...
research
10/21/2019

Conquering the CNN Over-Parameterization Dilemma: A Volterra Filtering Approach for Action Recognition

The importance of inference in Machine Learning (ML) has led to an explo...
research
03/23/2021

Learning Comprehensive Motion Representation for Action Recognition

For action recognition learning, 2D CNN-based methods are efficient but ...
research
02/10/2020

Joint Encoding of Appearance and Motion Features with Self-supervision for First Person Action Recognition

Wearable cameras are becoming more and more popular in several applicati...
research
04/01/2019

Dance with Flow: Two-in-One Stream Action Detection

The goal of this paper is to detect the spatio-temporal extent of an act...
research
08/10/2020

2nd Place Scheme on Action Recognition Track of ECCV 2020 VIPriors Challenges: An Efficient Optical Flow Stream Guided Framework

To address the problem of training on small datasets for action recognit...

Please sign up or login with your details

Forgot password? Click here to reset