TROY-VIS makes open-vocabulary video instance segmentation run in real time (around 25 FPS) while keeping accuracy comparable to or better than slower state-of-the-art models.
Xmem: Long- term video object segmentation with an atkinson-shiffrin memory model
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
2024 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Towards Real-Time Open-Vocabulary Video Instance Segmentation
TROY-VIS makes open-vocabulary video instance segmentation run in real time (around 25 FPS) while keeping accuracy comparable to or better than slower state-of-the-art models.