Published Paper Details:

Due to advancements in multimedia technology, video transmission now necessitates greater capacity for storage, more bandwidth, and faster transmission speeds. Compression methods for videos are crucial since they allow for content to be transmitted over less network capacity and with less room for storage. In addition to its widespread use in fields such as image and video analysis, NLP, speech recognition, etc., machine learning has just lately begun to find applications in BCI. Machine learning, which expedites training and boosts performance by drawing on information and precedents from similar situations, might be very helpful in BCI for accommodating differences between users and between jobs. Integrating cutting-edge machine learning technologies is another way to reap the benefits of both fields. This paper provides a comprehensive literature review and bibliometric study of all Machine Learning (ML) techniques that have been used to video compression in the recent past. Popular academic databases include Scopus and Web of Science. This analysis makes use of the data retrieved from them. There are two sorts of analysis done on the extracted data. You'll find both quantitative and qualitative findings. Quantitative analysis is the examination of records according to criteria such as the number of citations they include, the relevance of their keywords, the journals they were published in, and the countries in which those journals are based. The benefits, drawbacks, and difficulties of utilising ML-based techniques to video compression are detailed in the qualitative analysis provided.