Showing cs.CVShow all
2 papers · 1 filter
cs.CV2026
Towards Automatic Video Annotation with ASH: Zero-Shot Open-Vocabulary Multi-Object Tracking and Segmentation
Arash Rocky, Q. M. Jonathan Wu
Memory-attention-based Video Instance Segmentation (VIS) methods have demonstrated strong zero-shot tracking capability, yet their substantial memory requirements confine them to s…
cs.CV2025
SAM2Auto: Auto Annotation Using FLASH
Arash Rocky, Q. M. Jonathan Wu
Vision-Language Models (VLMs) lag behind Large Language Models due to the scarcity of annotated datasets, as creating paired visual-textual annotations is labor-intensive and expen…