Dense Correspondence Annotation of Video Data Using Non-Rigid Registration with Salient Feature Correspondence Constraints
碩士 === 國立臺灣大學 === 資訊工程學研究所 === 103 === There are a few existing annotation systems that aim to provide a platform for video annotation. Most of them focus on activity annotation while others concentrate on labeling individual objects. However, the latters focus on only labeling objects with bounding...
Main Authors: | Yen-Ting Chen, 陳彥廷 |
---|---|
Other Authors: | Chieh-Chih Wang |
Format: | Others |
Language: | en_US |
Published: |
2014
|
Online Access: | http://ndltd.ncl.edu.tw/handle/68845600289225045103 |
Similar Items
-
Learning local shape descriptors for computing non-rigid dense correspondence
by: Jianwei Guo, et al.
Published: (2020-03-01) -
Annotation Propagation in Large Image Databases via Dense Image Correspondence
by: Rubinstein, Michael, et al.
Published: (2021) -
Joint Inference in Weakly-Annotated Image Datasets via Dense Correspondence
by: Rubinstein, Michael, et al.
Published: (2017) -
A Novel Correspondence Selection Technique for Affine Rigid Image Registration
by: Guohua Lv
Published: (2018-01-01) -
Nonrigid registration with corresponding points constraint for automatic segmentation of cardiac DSCT images
by: Xuesong Lu, et al.
Published: (2017-03-01)