OV2VSS, a CLIP-based baseline with spatial-temporal fusion, random-frame enhancement, and video text encoding, segments novel categories in video and beats image-based methods on VSPW and Cityscapes zero-shot.
Difference-aware distillation for semantic segmenta- tion,
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.MM 1years
2024 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Towards Open-Vocabulary Video Semantic Segmentation
OV2VSS, a CLIP-based baseline with spatial-temporal fusion, random-frame enhancement, and video text encoding, segments novel categories in video and beats image-based methods on VSPW and Cityscapes zero-shot.