Effective action recognition with fully supervised and self-supervised methods

• 主要作者: Cao, Haozhi
• 其他作者: Mao Kezhi
• 格式: Thesis-Master by Research
• 語言: English
• 出版: Nanyang Technological University 2021
• 主題: Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence; Engineering::Computer science and engineering::Computing methodologies::Pattern recognition
• 在線閱讀: https://hdl.handle.net/10356/152741

Action recognition in videos has attracted interest in computer vision and machine learning communities thanks to its applications such as surveillance and smart homes. In addition to spatial information in individual frames, videos contain temporal information across the temporal dimension. Therefo...