Abstract | ||
---|---|---|
Heterogeneous domain adaptation (HDA) addresses the task of associating data not only across dissimilar domains but also described by different types of features. Inspired by the recent advances of neural networks and deep learning, we propose a deep leaning model of transfer neural trees (TNT), which jointly solves cross-domain feature mapping, adaptation, and classification in a unified architec... |
Year | DOI | Venue |
---|---|---|
2019 | 10.1109/TIP.2019.2912126 | IEEE Transactions on Image Processing |
Keywords | Field | DocType |
Task analysis,Artificial neural networks,Deep learning,Forestry,Training,Biological neural networks | Embedding,Task analysis,Feature mapping,Pattern recognition,Zero shot learning,Domain adaptation,Artificial intelligence,Deep learning,Artificial neural network,Random forest,Mathematics | Journal |
Volume | Issue | ISSN |
28 | 9 | 1057-7149 |
Citations | PageRank | References |
2 | 0.36 | 16 |
Authors | ||
5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Wei-Yu Chen | 1 | 51 | 2.75 |
Tzu-Ming Harry Hsu | 2 | 43 | 3.74 |
Yao-Hung Hubert Tsai | 3 | 32 | 5.22 |
Ming Chen | 4 | 6507 | 1277.71 |
Yu-Chiang Frank Wang | 5 | 914 | 61.63 |