Action-stage emphasized spatiotemporal VLAD for video action recognition

• Main Authors: Tu, Zhigang, Li, Hongyan, Zhang, Dejun, Dauwels, Justin, Li, Baoxin, Yuan, Junsong
• Other Authors: School of Electrical and Electronic Engineering
• Format: Article
• Language: English
• Published: 2021
• Subjects: Engineering::Electrical and electronic engineering; Action Recognition; Feature Encoding
• Online Access: https://hdl.handle.net/10356/150982
• Institution: Nanyang Technological University

Despite outstanding performance in image recognition, convolutional neural networks (CNNs) do not yet achieve the same impressive results on action recognition in videos. This is partially due to the inability of CNN for modeling long-range temporal structures especially those involving individual a...