Publication Type

Conference Proceeding Article

Version

publishedVersion

Publication Date

6-2021

Abstract

Unsupervised video object segmentation (UVOS) aims at segmenting the primary objects in videos without any human intervention. Due to the lack of prior knowledge about the primary objects, identifying them from videos is the major challenge of UVOS. Previous methods often regard the moving objects as primary ones and rely on optical flow to capture the motion cues in videos, but the flow information alone is insufficient to distinguish the primary objects from the background objects that move together. This is because, when the noisy motion features are combined with the appearance features, the localization of the primary objects is misguided. To address this problem, we propose a novel reciprocal transformation network to discover primary objects by correlating three key factors: the intra-frame contrast, the motion cues, and temporal coherence of recurring objects. Each corresponds to a representative type of primary object, and our reciprocal mechanism enables an organic coordination of them to effectively remove ambiguous distractions from videos. Additionally, to exclude the information of the moving background objects from motion features, our transformation module enables to reciprocally transform the appearance features to enhance the motion features, so as to focus on the moving objects with salient appearance while removing the co-moving outliers. Experiments on the public benchmarks demonstrate that our model significantly outperforms the state-of-the-art methods. Code is available at https://github.com/OliverRensu/RTNet.

Keywords

Computer vision, Image segmentation, Background objects, Flow informations, Human intervention, Key factors, Localisation, Motion cues, Motion features, Moving objects, Prior-knowledge, Video objects segmentations

Discipline

Databases and Information Systems | Graphics and Human Computer Interfaces

Research Areas

Information Systems and Management; Intelligent Systems and Optimization

Publication

Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (CVPR)

First Page

15430

Last Page

15439

ISBN

9781665445108

Identifier

10.1109/CVPR46437.2021.01520

Publisher

IEEE

City or Country

USA

Copyright Owner and License

Authors

Download

Share

COinS