Institutional Repository of Vilnius University
Mašininiu mokymusi pagrįstos sistemos, identifikuojančios reklamas vaizdo įrašuose, kūrimas /
Abstract
dc:descriptionThe main goal of this work is to create a system based on machine learning, which would detect and skip adds in YouTube video content. During this work, these tasks were performed: an analysis of similar systems, creation of functional, non-functional and user requirements for an add detection system, creation of systems mock ups, the fine-tuning of a BERT model for add detection and creation of the main system components: the server, the database, the user interface and the text classifier which all together create a functioning system that can detect and skip adds in video content. During this project, the system was successfully implemented. During the systems creation, valuable skills and knowledge about web development and working with machine learning models were gained.
Degree
thesis:*- Grantor dc:publisher
- Institutional Repository of Vilnius University
- Year dc:date
- 2024
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Kvedaravičius, Karolis,
Rights
dc:rights- Statement dc:rights
-
- info:eu-repo/semantics/openAccess
- Language dc:language
- lit
Identifiers
dc:identifier.*- Repository record dc:identifier
- https://repository.vu.lt/VU:ELABAETD210647118&prefLang=en_US