Title
Joint Semantic and Latent Attribute Modelling for Cross-Class Transfer Learning.
Abstract
A number of vision problems such as zero-shot learning and person re-identification can be considered as cross-class transfer learning problems. As mid-level semantic properties shared cross different object classes, attributes have been studied extensively for knowledge transfer across classes. Most previous attribute learning methods focus only on human-defined/nameable semantic attributes, whil...
Year
DOI
Venue
2018
10.1109/TPAMI.2017.2723882
IEEE Transactions on Pattern Analysis and Machine Intelligence
Keywords
Field
DocType
Semantics,Dictionaries,Training,Visualization,Computational modeling,Adaptation models,Data models
Algorithmic learning theory,Instance-based learning,Stability (learning theory),Multi-task learning,Inductive transfer,Active learning (machine learning),Computer science,Transfer of learning,Unsupervised learning,Natural language processing,Artificial intelligence,Machine learning
Journal
Volume
Issue
ISSN
40
7
0162-8828
Citations 
PageRank 
References 
15
0.59
60
Authors
6
Name
Order
Citations
PageRank
Peixi Peng1746.85
Yonghong Tian21057102.81
Tao Xiang34929215.84
Yaowei Wang413429.62
Massimiliano Pontil55820472.96
Tiejun Huang61281120.48