Error recovered hierarchical classification
Hierarchical classification (HC) is a popular and efficient way for detecting the semantic concepts from the images. However, the conventional HC, which always selects the branch with the highest classification response to go on, has the risk of propagating serious errors from higher levels of the h...
Saved in:
Main Authors: | ZHU, Shiai, WEI, Xiao-Yong, NGO, Chong-wah |
---|---|
Format: | text |
Language: | English |
Published: |
Institutional Knowledge at Singapore Management University
2013
|
Subjects: | |
Online Access: | https://ink.library.smu.edu.sg/sis_research/6517 https://ink.library.smu.edu.sg/context/sis_research/article/7520/viewcontent/2502081.2502182.pdf |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Singapore Management University |
Language: | English |
Similar Items
-
Collaborative error reduction for hierarchical classification
by: ZHU, Shiai, et al.
Published: (2014) -
On the sampling of web images for learning visual concept classifiers
by: ZHU, Shiai, et al.
Published: (2010) -
Predicting domain adaptivity: Redo or recycle?
by: YAO, Ting, et al.
Published: (2012) -
On the pooling of positive examples with ontology for visual concept learning
by: ZHU, Shiai, et al.
Published: (2011) -
Video concept detection by learning from web images: A case study on cross domain learning
by: ZHU, Shiai, et al.
Published: (2013)