JVLGS fuses text prompts with video features and a morphological post-processing step to achieve state-of-the-art gas leak segmentation on SimGas and a new few-shot IGS split.
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
background 1representative citing papers
citing papers explorer
-
JVLGS: Joint Vision-Language Gas Leak Segmentation
JVLGS fuses text prompts with video features and a morphological post-processing step to achieve state-of-the-art gas leak segmentation on SimGas and a new few-shot IGS split.