Video instance segmentation (VIS) is a critical task with diverse applications, including
autonomous driving and video editing. Existing methods often underperform on complex …

The Segment Anything Model (SAM) has established itself as a powerful zero-shot image
segmentation model, employing interactive prompts such as points to generate masks. This …

In recent years, significant progress has been made in video instance segmentation (VIS),
with many offline and online methods achieving state-of-the-art performance. While offline …

Temporally locating objects with arbitrary class texts is the primary pursuit of open-
vocabulary Video Instance Segmentation (VIS). Because of the insufficient vocabulary of …

Recent trends in Video Instance Segmentation (VIS) have seen a growing reliance on online
methods to model complex and lengthy video sequences. However, the degradation of …

Recently, Transformer-based offline video instance segmentation (VIS) solutions have made
significant progress by decomposing the whole task into global segmentation map …

Recently, promptable segmentation models, such as the Segment Anything Model (SAM),
have demonstrated robust zero-shot generalization capabilities on static images. These …

Amodal perception is the important ability of humans to imagine the entire shape of
occluded objects. This ability is crucial for safety-relevant perception tasks such as …

Abstract Video Instance Segmentation (VIS) has seen a growing reliance on query
propagation-based methods to model complex and lengthy videos. While these methods …