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 module (DAM) and a temporal aggregation module (TAM). DAM resolves the domain gap between two modalities by forcing the values to be in the same range using a cross-correlation mechanism. TAM captures long-term coherence by extracting and leveraging global cues of a video. On public benchmark datasets, our proposed approach demonstrates its effectiveness, outperforming all existing methods by a substantial margin.
View on arXiv