Dynamic Warping Network for Semantic Video Segmentation

A major challenge for semantic video segmentation is how to exploit the spatiotemporal information and produce consistent results for a video sequence. Many previous works utilize the precomputed optical flow to warp the feature maps across adjacent frames. However, the imprecise optical flow and th...

Full description

Saved in:
Bibliographic Details
Main Authors: Jiangyun Li, Yikai Zhao, Xingjian He, Xinxin Zhu, Jing Liu
Format: Article
Language:English
Published: Wiley 2021-01-01
Series:Complexity
Online Access:http://dx.doi.org/10.1155/2021/6680509
Tags: Add Tag
No Tags, Be the first to tag this record!