Leveraging Motion Priors in Videos for Improving Human Segmentation across Domains
碩士 === 國立清華大學 === 電機工程學系所 === 106 === Despite many advances in deep-learning based semantic segmentation, performance drop due to distribution mismatch is often encountered in the real world. Recently, a few domain adaptations and active learning approaches have been proposed to mitigate the perform...
Main Authors: | Chen, Yu-Ting, 陳玉亭 |
---|---|
Other Authors: | Sun, Min |
Format: | Others |
Language: | en_US |
Published: |
2018
|
Online Access: | http://ndltd.ncl.edu.tw/handle/5ybxyn |
Similar Items
-
Leveraging Motion Information for Improving Domain Adaptation in Human Segmentation
by: Lu, Hai-Lun, et al.
Published: (2019) -
Video Segmentation with Motion Smoothness
by: Chung-Lin Wen, et al.
Published: (2009) -
Frequency-Domain-Based Human Motion Analysis in Surveillance Videos
by: Chang-sian Chen, et al.
Published: (2008) -
A Study on Segmentation for Motion Video
by: Song-Yi Tsai, et al.
Published: (1999) -
Leveraging the Domain of Work to Improve Migrant Health
by: Michael A. Flynn, et al.
Published: (2017-10-01)