Preprint
Oct 2026
When Trackers Fail: VLM-Guided Verification and Recovery for Robust Video Object Segmentation
Recent trackers built on foundation models such as the Segment Anything Model (SAM) achieve strong performance by propagating object masks through memory. However, this strength is also a key source of failure: under occlusion, reappearance, or distractors, an incorrect prediction can enter the tracking loop and be pro...
Valay Bundele, Susmit Agrawal, Mehran Hosseinzadeh et al.
· 1 citation