InterRVOS extends referring video object segmentation to segment both actor and target objects separately for interaction expressions, with a new dataset and MLLM-based method.
Mevis: A large-scale benchmark for video segmentation with motion expressions
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
InterRVOS: Interaction-aware Referring Video Object Segmentation
InterRVOS extends referring video object segmentation to segment both actor and target objects separately for interaction expressions, with a new dataset and MLLM-based method.