NDLI: Joint attribute chain prediction for zero-shot learning

Content Provider	IET Digital Library
Author	Qiao, Lingfeng Tuo, Hongya Wang, Jiexin Wang, Chao Jing, Zhongliang
Abstract	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, the authors explore the relationship between attributes and propose Joint Attribute Chain Prediction (JACP). Attribute chains are introduced to represent the relations. Conditional probabilities of attributes are estimated orderly along the chain to calculate the joint posteriors of the testing classes without independence assumptions. To reduce the estimation error, attribute relation clustering algorithm is presented to group the long chain into some unrelated small chains. When the max length of chains is one, JACP is essentially identical with DAP. Experiments on three data sets for zero-shot problem demonstrate the classification accuracy and efficiency of the authors’ algorithm. The results show that mining attribute relations can greatly improve the performance of ZSL effectively.
Starting Page	873
Ending Page	881
Page Count	9
ISSN	17519632
Volume Number	12
e-ISSN	17519640
Issue Number	Issue 6, Sep (2018)
Alternate Webpage(s)	https://digital-library.theiet.org/content/journals/iet-cvi/12/6
Alternate Webpage(s)	https://digital-library.theiet.org/content/journals/10.1049/iet-cvi.2017.0438
Journal	IET Computer Vision
Publisher Date	2018-04-26
Access Restriction	Open
Rights Holder	© The Institution of Engineering and Technology
Subject Keyword	Attribute Relation Clustering Algorithm Attribute Relation Mining Classification Accuracy Computer Vision And Image Processing Technique Conditional Probabilities Data Mining Direct Attribute Prediction Estimation Error Reduction Image Classification Image Recognition JACP Joint Attribute Chain Prediction Knowledge Engineering Technique Learning in AI Probability Statistics Zero-shot Learning ZSL Method
Content Type	Text
Resource Type	Article
Subject	Computer Vision and Pattern Recognition Software

Sl.	Authority	Responsibilities	Communication Details
1	Ministry of Education (GoI), Department of Higher Education	Sanctioning Authority	https://www.education.gov.in/ict-initiatives
2	Indian Institute of Technology Kharagpur	Host Institute of the Project: The host institute of the project is responsible for providing infrastructure support and hosting the project	https://www.iitkgp.ac.in
3	National Digital Library of India Office, Indian Institute of Technology Kharagpur	The administrative and infrastructural headquarters of the project	Dr. B. Sutradhar bsutra@ndl.gov.in
4	Project PI / Joint PI	Principal Investigator and Joint Principal Investigators of the project	Dr. B. Sutradhar bsutra@ndl.gov.in Prof. Saswat Chakrabarti will be added soon
5	Website/Portal (Helpdesk)	Queries regarding NDLI and its services	support@ndl.gov.in
6	Contents and Copyright Issues	Queries related to content curation and copyright issues	content@ndl.gov.in
7	National Digital Library of India Club (NDLI Club)	Queries related to NDLI Club formation, support, user awareness program, seminar/symposium, collaboration, social media, promotion, and outreach	clubsupport@ndl.gov.in
8	Digital Preservation Centre (DPC)	Assistance with digitizing and archiving copyright-free printed books	dpc@ndl.gov.in
9	IDR Setup or Support	Queries related to establishment and support of Institutional Digital Repository (IDR) and IDR workshops	idr@ndl.gov.in

Attribute relaxation from class level to instance level for zero-shot learning

Zero-shot learning by exploiting class-related and attribute-related prior knowledge

Unbiased hybrid generation network for zero-shot learning

HFM: A Hybrid Feature Model Based on Conditional Auto Encoders for Zero-Shot Learning

Automatic metrics learning with low-noise embedding for zero-shot learning

Zero-shot multi-label learning via label factorisation

SEER-ZSL: Semantic Encoder-Enhanced Representations for Generalized Zero-Shot Learning

Relation-aware Compositional Zero-shot Learning for Attribute-Object Pair Recognition

Zero-Shot Action Recognition with Three-Stream Graph Convolutional Networks

Joint attribute chain prediction for zero-shot learning

Similar Documents

Attribute relaxation from class level to instance level for zero-shot learning

Zero-shot learning by exploiting class-related and attribute-related prior knowledge

Unbiased hybrid generation network for zero-shot learning

HFM: A Hybrid Feature Model Based on Conditional Auto Encoders for Zero-Shot Learning

Automatic metrics learning with low-noise embedding for zero-shot learning

Zero-shot multi-label learning via label factorisation

SEER-ZSL: Semantic Encoder-Enhanced Representations for Generalized Zero-Shot Learning

Relation-aware Compositional Zero-shot Learning for Attribute-Object Pair Recognition

Zero-Shot Action Recognition with Three-Stream Graph Convolutional Networks

Joint attribute chain prediction for zero-shot learning