Dual Prototype Attention for Unsupervised Video Object Segmentation

arXiv:2211.12036v3 Announce Type: replace
Abstract: Unsupervised video object segmentation (VOS) aims to detect and segment the most salient object in videos. The primary techniques used in unsupervised VOS are 1) the collaboration of appearance and motion information; and 2) temporal fusion between different frames. This paper proposes two novel prototype-based attention mechanisms, inter-modality attention (IMA) and inter-frame attention (IFA), to incorporate these techniques via dense propagation across different modalities and frames. IMA densely integrates context information from different modalities based …

abstract arxiv attention attention mechanisms collaboration cs.cv fusion information novel object paper segment segmentation temporal type unsupervised video videos