FAST-VQA: efficient end-to-end video quality assessment with fragment sampling

• Main Authors: Wu, Haoning, Chen, Chaofeng, Hou, Jingwen, Liao, Liang, Wang, Annan, Sun, Wenxiu, Yan, Qiong, Lin, Weisi
• Other Authors: College of Computing and Data Science
• Format: Conference or Workshop Item
• Language: English
• Published: 2024
• Subjects: Computer and Information Science; Video quality assessment; Fragments
• Online Access: https://hdl.handle.net/10356/178453; https://link.springer.com/chapter/10.1007/978-3-031-20068-7_31
• Institution: Nanyang Technological University

Current deep video quality assessment (VQA) methods are usually with high computational costs when evaluating high-resolution videos. This cost hinders them from learning better video-quality-related representations via end-to-end training. Existing approaches typically consider naive sampling to re...