Joint attribute chain prediction for zero‐shot learning

Joint attribute chain prediction for zero‐shot learning

Zero‐shot learning (ZSL) aims to classify the objects without any training samples. Attributes are used to transfer knowledge from the training set to testing one in ZSL. Most ZSL methods based on Direct Attribute Prediction (DAP) assume that attributes are independent of each other. In this study,...

Full description

Bibliographic Details
Main Authors: Lingfeng Qiao, Hongya Tuo, Jiexin Wang, Chao Wang, Zhongliang Jing
Format: Article
Language:English
Published: Wiley 2018-09-01
Series:IET Computer Vision
Subjects:
joint attribute chain prediction
zero-shot learning
ZSL methods
direct attribute prediction
JACP
conditional probabilities
Online Access:https://doi.org/10.1049/iet-cvi.2017.0438

Internet

https://doi.org/10.1049/iet-cvi.2017.0438

Similar Items