all AI news
Domain Alignment and Temporal Aggregation for Unsupervised Video Object Segmentation. (arXiv:2211.12036v1 [cs.CV])
cs.CV updates on arXiv.org arxiv.org
Unsupervised video object segmentation aims at detecting and segmenting the
most salient object in videos. In recent times, two-stream approaches that
collaboratively leverage appearance cues and motion cues have attracted
extensive attention thanks to their powerful performance. However, there are
two limitations faced by those methods: 1) the domain gap between appearance
and motion information is not well considered; and 2) long-term temporal
coherence within a video sequence is not exploited. To overcome these
limitations, we propose a domain alignment …
aggregation alignment arxiv segmentation temporal unsupervised video