A Novel Double-Layer Framework for Action Prediction

A Novel Double-Layer Framework for Action Prediction

Action prediction aims to infer the category of an action before it is fully executed. It is a challenging task since neither sufficient discriminative information nor the definite progress state of action can be obtained in an incomplete video. In this paper, we propose a novel double-layer learnin...

Full description

Bibliographic Details
Main Authors: Cuiwei Liu, Yaguang Lu, Xiangbin Shi, Chong Du, Zhaokui Li
Format: Article
Language:English
Published: IEEE 2019-01-01
Series:IEEE Access
Subjects:
Action prediction
double-layer learning framework
unsupervised semantic reasoning method
latent discriminative action prediction model
Online Access:https://ieeexplore.ieee.org/document/8917561/

Internet

https://ieeexplore.ieee.org/document/8917561/

Similar Items