Artificial intelligence, specially deep learning (DL)-based computer vision algorithms has been revolutionizing video generation, enabling the creation of realistic videos through advanced algorithms specially through DL models. These AI-generated videos bring opportunities in many industries and individual content creators but also bring major threats to humanity for misuse as deepfakes. This tutorial paper overviews the methodologies driving AI-generated videos and its underlying key technologies. It briefly explores the foundational roles of Generative Adversarial Networks, Diffusion Model, and Autoencoders and their backbone DL algorithms in synthesizing video content. The paper also briefly discussed the opportunities of generated videos as well as potential threats in the era of deepfakes. It also discussed significant challenges, ethical considerations, and future directions for enhancing control and creativity in AI video generation. The content will be updated in successive versions of the paper from time to time as the state-of-the-art progresses.

The usability of computer vision is everywhere, whereas deep learning revolutionized the concept of artificial intelligence including computer vision. This paper discusses the leverages of deep learning for computer vision. At first, the background details of computer vision and deep learning have been discussed. Important tasks of computer vision like image classification, object localization, object detection, segmentation are briefly explained. Various types of deep learning algorithms have been described. The architecture of the convolutional neural network$ has been explained briefly. Applications of deep learning in different fields of computer vision like image classifications, human activity recognition, scene text detection and recognition, object tracking, visual question answering, etc., have been discussed with the references of the recent state-of-the-art works.

Highlights of the article are: • Presented a systematic study of Deep Learning (DL), Deep Transfer Learning (DTL) and Edge Computing(EC) to mitigate COVID-19. • Surveyed on existing DL, DTL, EC, and Dataset to mitigate pandemics with potentialities and challenges. • Drawn a precedent pipeline model of DTL over EC for a future scope to mitigate any outbreaks. • Given brief analyses and challenges wherever relevant in perspective of COVID-19.