SAMannot delivers a memory-efficient local framework for interactive video instance segmentation by optimizing SAM2 with persistent identity tracking, lock-and-refine workflows, and auto-prompting.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
SAMannot: A Memory-Efficient, Local, Open-source Framework for Interactive Video Instance Segmentation based on SAM2
SAMannot delivers a memory-efficient local framework for interactive video instance segmentation by optimizing SAM2 with persistent identity tracking, lock-and-refine workflows, and auto-prompting.