A SAM 2-based model with BEiT-3-derived mask priors and global-historical aggregation achieves state-of-the-art referring video object segmentation on Ref-YouTube-VOS, MeViS, and Ref-DAVIS17.
Xmem++: Production-level video segmentation from few annotated frames
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
MPG-SAM 2: Adapting SAM 2 with Mask Priors and Global Context for Referring Video Object Segmentation
A SAM 2-based model with BEiT-3-derived mask priors and global-historical aggregation achieves state-of-the-art referring video object segmentation on Ref-YouTube-VOS, MeViS, and Ref-DAVIS17.