OneVOS: Unifying Video Object Segmentation with All-in-One Transformer Framework

arXiv:2403.08682v1 Announce Type: new
Abstract: Contemporary Video Object Segmentation (VOS) approaches typically consist stages of feature extraction, matching, memory management, and multiple objects aggregation. Recent advanced models either employ a discrete modeling for these components in a sequential manner, or optimize a combined pipeline through substructure aggregation. However, these existing explicit staged approaches prevent the VOS framework from being optimized as a unified whole, leading to the limited capacity and suboptimal performance in tackling complex videos. In this paper, we …

abstract advanced aggregation arxiv components cs.cv extraction feature feature extraction framework however management memory modeling multiple object objects pipeline segmentation through transformer type video