We present Segment Anything Model 2 (SAM 2), a foundation model towards solving
promptable visual segmentation in images and videos. We build a data engine, which …

Tracking any given object (s) spatially and temporally is a common purpose in Visual Object
Tracking (VOT) and Video Object Segmentation (VOS). Joint tracking and segmentation …

Current universal segmentation methods demonstrate strong capabilities in pixel-level
image and video understanding. However, they lack reasoning abilities and cannot be …

Open-Vocabulary Video Instance Segmentation (VIS) is attracting increasing attention due
to its ability to segment and track arbitrary objects. However, the recent Open-Vocabulary …

Medical image segmentation is crucial in accurately identifying and delineating regions of
interest in medical images, which can inform the diagnosis and treatment of various …

In the realm of medical image analysis, where challenges like high class imbalance, inter-
class similarity, and intra-class variance are prevalent, knowledge distillation has emerged …

Abstract Weakly Supervised Video Anomaly Detection (WSVAD) plays a crucial role in
visual surveillance by effectively distinguishing anomalies from normality with only video …

Memory-based networks have achieved tremendous success in video object segmentation.
However, these methods still suffer from unfaithful segmentation and inferior efficiency under …

Motion Expression guided Video Segmentation (MeViS), as an emerging task, poses many
new challenges to the field of referring video object segmentation (RVOS). In this technical …

We focus on the challenging problem of learning an unbiased classifier from a large number
of potentially relevant but noisily labeled web images given only a few clean labeled …