Spatio-Temporal Human Action Recognition Modelwith Flexible-interval Sampling and Normalization

08/12/2021
by   , et al.
0

Human action recognition is a well-known computer vision and pattern recognition task of identifying which action a man is actually doing. Extracting the keypoint information of a single human with both spatial and temporal features of action sequences plays an essential role to accomplish the task.In this paper, we propose a human action system for Red-Green-Blue(RGB) input video with our own designed module. Based on the efficient Gated Recurrent Unit(GRU) for spatio-temporal feature extraction, we add another sampling module and normalization module to improve the performance of the model in order to recognize the human actions. Furthermore, we build a novel dataset with a similar background and discriminative actions for both human keypoint prediction and behavior recognition. To get a better result, we retrain the pose model with our new dataset to get better performance. Experimental results demonstrate the effectiveness of the proposed model on our own human behavior recognition dataset and some public datasets.

READ FULL TEXT
research
11/18/2016

An End-to-End Spatio-Temporal Attention Model for Human Action Recognition from Skeleton Data

Human action recognition is an important task in computer vision. Extrac...
research
10/06/2021

SAIC_Cambridge-HuPBA-FBK Submission to the EPIC-Kitchens-100 Action Recognition Challenge 2021

This report presents the technical details of our submission to the EPIC...
research
01/29/2020

Human Action Performance using Deep Neuro-Fuzzy Recurrent Attention Model

A great number of computer vision publications have focused on distingui...
research
12/03/2018

Feature Extraction for Temporal Signal Recognition: An Overview

Due to the huge progress of the recording devices, data from heterogeneo...
research
08/27/2012

Are You Imitating Me? Unsupervised Sparse Modeling for Group Activity Analysis from a Single Video

A framework for unsupervised group activity analysis from a single video...
research
10/21/2017

A Generative Restricted Boltzmann Machine Based Method for High-Dimensional Motion Data Modeling

Many computer vision applications involve modeling complex spatio-tempor...
research
09/19/2017

Human Action Forecasting by Learning Task Grammars

For effective human-robot interaction, it is important that a robotic as...

Please sign up or login with your details

Forgot password? Click here to reset