Vision-language-model-based video quality assessment

• Main Author: Zhang, Erli
• Other Authors: Lin Weisi
• Format: Final Year Project
• Language: English
• Published: Nanyang Technological University 2024
• Subjects: Computer and Information Science; Artificial intelligence; Video quality analysis
• Online Access: https://hdl.handle.net/10356/175035
• Institution: Nanyang Technological University

This work introduces a comprehensive approach to video quality assessment (VQA) by both traditional deep-learning-based methods as well as vision-language-model-based methods. Through the development of the DIVIDE-3k database and the DOVER model, we offer nuanced insights into the multifaceted natur...