Multilabel prediction via cross-view search
Embedding methods have shown promising performance in multilabel prediction, as they are able to discover the label dependence. However, most methods ignore the correlations between the input and output, such that their learned embeddings are not well aligned, which leads to degradation in predictio...
Saved in:
Main Authors: | Shen, Xiaobo, Liu, Weiwei, Tsang, Ivor W., Sun, Quan-Sen, Ong, Yew-Soon |
---|---|
Other Authors: | School of Computer Science and Engineering |
Format: | Article |
Language: | English |
Published: |
2020
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/139886 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
Similar Items
-
Click-through-based cross-view learning for image search
by: PAN, Yingwei, et al.
Published: (2014) -
Arbitrary-view human action recognition for human robot interaction
by: Loh, Zachariah Jin Jun
Published: (2024) -
Materialized view maintenance for XML documents
by: FA YUAN
Published: (2010) -
Image decomposition with multilabel context: Algorithms and applications
by: Li, T., et al.
Published: (2014) -
A multilabel text classification algorithm for labeling risk factors in sec form 10-K
by: Huang, K.-W., et al.
Published: (2013)