2 papers
cs.CV2020
Hybrid-S2S: Video Object Segmentation with Recurrent Networks and Correspondence Matching
Fatemeh Azimi, Stanislav Frolov, Federico Raue +2
One-shot Video Object Segmentation~(VOS) is the task of pixel-wise tracking an object of interest within a video sequence, where the segmentation mask of the first frame is given a…
cs.CV2020
Revisiting Sequence-to-Sequence Video Object Segmentation with Multi-Task Loss and Skip-Memory
Fatemeh Azimi, Benjamin Bischke, Sebastian Palacio +3
Video Object Segmentation (VOS) is an active research area of the visual domain. One of its fundamental sub-tasks is semi-supervised / one-shot learning: given only the segmentatio…