Local fusion networks with chained residual pooling for video action recognition

• Main Authors: He, Feixiang, Liu, Fayao, Yao, Rui, Lin, Guosheng
• 其他作者: School of Computer Science and Engineering
• 格式: Article
• 語言: English
• 出版: 2020
• 主題: Engineering::Computer science and engineering; Action Recognition; Residual Connection
• 在線閱讀: https://hdl.handle.net/10356/143069
• 機構: Nanyang Technological University

Action recognition is an important yet challenging problem. We here present a novel method, multistage local fusion networks with residual connections, to boost the performance of video action recognition. In realistic videos, an action instance may have a long time span and some frames may suffer f...