DMM-Net: Differentiable Mask-Matching Network for Video Object Segmentation

In this paper, we propose the differentiable mask-matching network (DMM-Net) for solving the video object segmentation problem where the initial object masks are provided. Relying on the Mask R-CNN backbone, we extract mask proposals per frame and formulate the matching between object templates and...

Full description

Bibliographic Details

Published in:	Proceedings / IEEE International Conference on Computer Vision pp. 3928 - 3937
Main Authors:	Zeng, Xiaohui, Liao, Renjie, Gu, Li, Xiong, Yuwen, Fidler, Sanja, Urtasun, Raquel
Format:	Conference Proceeding
Language:	English
Published:	IEEE 01.10.2019
Subjects:	Feature extraction Inference algorithms Object segmentation Prediction algorithms Proposals Strain Task analysis
ISSN:	2380-7504
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!