Learning Attention-Enhanced Spatiotemporal Representation for Action Recognition

Learning Attention-Enhanced Spatiotemporal Representation for Action Recognition

Learning spatiotemporal features via 3D-CNN (3D Convolutional Neural Network) models has been regarded as an effective approach for action recognition. In this paper, we explore visual attention mechanism for video analysis and propose a novel 3D-CNN model, dubbed AE-I3D (Attention-Enhanced Inflated...

Full description

Bibliographic Details
Main Authors: Zhensheng Shi, Liangjie Cao, Cheng Guan, Haiyong Zheng, Zhaorui Gu, Zhibin Yu, Bing Zheng
Format: Article
Language:English
Published: IEEE 2020-01-01
Series:IEEE Access
Subjects:
Action recognition
video understanding
spatiotemporal representation
visual attention
3D-CNN
residual learning
Online Access:https://ieeexplore.ieee.org/document/8963915/

Internet

https://ieeexplore.ieee.org/document/8963915/

Similar Items