Video Classification with a CNN-RNN Architecture | Human Activity Recognition

Video Classification is the task of predicting a label that is relevant to the video.

Github: https://github.com/AarohiSingla/Video...

Topics which I will cover in this Video Classification Tutorial are:
Overview of Video Classification
Steps to build our own Video Classification model
Exploring the Video Classification dataset
Training our Video Classification Model
Evaluating our Video Classification Model

#############################################
In case of any query, You can comment or you can contact me at [email protected]
############################################


What are videos?

Videos are a collection of images(frames) arranged in a specific order.

In Image classification: we take images, use feature extractors (like convolutional neural networks or CNNs) to extract features from images, and then classify that image based on these extracted features.  Video classification involves just one extra step.

While performing Video classification:
1- We first extract frames from the given video.
2- use feature extractors (like convolutional neural networks or CNNs) to extract features from all the frames,
3- Classify every frame based on these extracted features.

Before we talk about Video Classification, let us first understand what is Human Activity Recognition?.
The task of classifying or predicting the activity/action performed by someone is called Activity recognition.

With the help of Video Classification models we can solve the problem of Human Activity Recognition.


#VideoClassifier #VideoClassification #HumanActivityRecognition #CNN #RNN #AI #ComputerVision #DeepLearning #ArtificialIntelligence





Join this channel to get access to perks:
   / @codewithaarohi