This report presents a framework called Segment And Track Anything (SAMTrack) that
allows users to precisely and effectively segment and track any object in a video …

Zero-shot video object segmentation (ZS-VOS) aims to segment foreground objects in a
video sequence without prior knowledge of these objects. However, existing ZS-VOS …

For the video salient object detection (VSOD) task, how to excavate the information from the
appearance modality and the motion modality has always been a topic of great concern. The …

Abstract Zero-shot Video Object Segmentation (ZSVOS) aims at segmenting the primary
moving object without any human annotations. Mainstream solutions mainly focus on …

The optical flow guidance strategy is ideal for obtaining motion information of objects in the
video. It is widely utilized in video segmentation tasks. However, existing optical flow-based …

Tracking and following objects of interest is critical to several robotics use cases, ranging
from industrial automation to logistics and warehousing, to healthcare and security. In this …

The existing unsupervised video object segmentation methods depend heavily on the
segmentation model trained offline on a labeled training video set, and cannot well …

Abstract Unsupervised Video Object Segmentation (VOS) aims at identifying the contours of
primary foreground objects in videos without any prior knowledge. However, previous …

Unsupervised video object segmentation has made significant progress in recent years, but
the manual annotation of video mask datasets is expensive and limits the diversity of …

Unsupervised video object segmentation (UVOS) aims at detecting the primary objects in a
given video sequence without any human interposing. Most existing methods rely on two …