DMVOS : Discriminative Matching for Real-time Video Object Segmentation

Peisong WEN, Ruolin YANG, Qianqian XU, Chen QIAN, Qingming HUANG, Runmin CONG, Jianlou SI*

*Corresponding author for this work

Research output: Book Chapters | Papers in Conference ProceedingsConference paper (refereed)Referred Conference Paperpeer-review

13 Citations (Scopus)

Abstract

Though recent methods on semi-supervised video object segmentation (VOS) have achieved an appreciable improvement of segmentation accuracy, it is still hard to get an adequate speed-accuracy balance when facing real-world application scenarios. In this work, we propose Discriminative Matching for real-time Video Object Segmentation (DMVOS), a real-time VOS framework with high-accuracy to fill this gap. Based on the matching mechanism, our framework introduces discriminative information through the Isometric Correlation module and the Instance Center Offset module. Specifically, the isometric correlation module learns a pixel-level similarity map with semantic discriminability, and the instance center offset module is applied to exploit the instance-level spatial discriminability. Experiments on two benchmark datasets show that our model achieves state-of-the-art performance with extremely fast speed, for example, J&F of 87.8% on DAVIS-2016 validation set with 35 milliseconds per frame.

Original languageEnglish
Title of host publicationProceedings : 28th ACM International Conference on Multimedia, MM 2020
PublisherAssociation for Computing Machinery, Inc
Pages2048-2056
Number of pages9
ISBN (Electronic)9781450379885
DOIs
Publication statusPublished - Oct 2020
Externally publishedYes
Event28th ACM International Conference on Multimedia, MM 2020 - Virtual, Online, United States
Duration: 12 Oct 202016 Oct 2020

Conference

Conference28th ACM International Conference on Multimedia, MM 2020
Country/TerritoryUnited States
CityVirtual, Online
Period12/10/2016/10/20

Bibliographical note

Publisher Copyright:
© 2020 ACM.

Keywords

  • instance center offset
  • isometric matching
  • real-time tracker
  • video object segmentation

Fingerprint

Dive into the research topics of 'DMVOS : Discriminative Matching for Real-time Video Object Segmentation'. Together they form a unique fingerprint.

Cite this