Dynamic Action Recognition: A convolutional neural network model for temporally organized joint location data

by   Adhavan Jayabalan, et al.

Motivation: Recognizing human actions in a video is a challenging task which has applications in various fields. Previous works in this area have either used images from a 2D or 3D camera. Few have used the idea that human actions can be easily identified by the movement of the joints in the 3D space and instead used a Recurrent Neural Network (RNN) for modeling. Convolutional neural networks (CNN) have the ability to recognise even the complex patterns in data which makes it suitable for detecting human actions. Thus, we modeled a CNN which can predict the human activity using the joint data. Furthermore, using the joint data representation has the benefit of lower dimensionality than image or video representations. This makes our model simpler and faster than the RNN models. In this study, we have developed a six layer convolutional network, which reduces each input feature vector of the form 15x1961x4 to an one dimensional binary vector which gives us the predicted activity. Results: Our model is able to recognise an activity correctly upto 87 data is taken from the Cornell Activity Datasets which have day to day activities like talking, relaxing, eating, cooking etc.


page 1

page 2

page 7

page 11


Action Recognition with Joint Attention on Multi-Level Deep Features

We propose a novel deep supervised neural network for the task of action...

Human Activity Recognition Using Multichannel Convolutional Neural Network

Human Activity Recognition (HAR) simply refers to the capacity of a mach...

Temporal Activity Detection in Untrimmed Videos with Recurrent Neural Networks

This thesis explore different approaches using Convolutional and Recurre...

Action Recognition with Image Based CNN Features

Most of human actions consist of complex temporal compositions of more s...

Predicting Daily Activities From Egocentric Images Using Deep Learning

We present a method to analyze images taken from a passive egocentric we...

Tied Reduced RNN-T Decoder

Previous works on the Recurrent Neural Network-Transducer (RNN-T) models...

Learning Intermediate Features of Object Affordances with a Convolutional Neural Network

Our ability to interact with the world around us relies on being able to...

Please sign up or login with your details

Forgot password? Click here to reset