• Tushar Lal
• M S Srividya
• Anala M R
• Shalini R
• Ramyashree V

This paper aims to identify the various actions and expressions portrayed by a human in the input video stream. Firstly, we extract frames from the input video stream and then perform background subtraction. The frames are then pre-processed and fed to the trained CNN model (AlexNet). The proposed method aims to build two CNN models where in the first model identifies human action and the second model identifies human expression. Finally, as a result, we integrate both the models and use the soft-max classifier to classify the identified actions and expressions accordingly to their classes.

Human activity recognition,soft-max classifier,Histograms of Oriented Gradients,Adam optimizer

"Human Action Recognition using Multimodal CNN ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.8, Issue 6, page no.c128-c132, June-2021, Available :http://www.jetir.org/papers/JETIR2106286.pdf

"Human Action Recognition using Multimodal CNN ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.8, Issue 6, page no. ppc128-c132, June-2021, Available at : http://www.jetir.org/papers/JETIR2106286.pdf