Recently integrating video foundation models and large language models to build a video
understanding system can overcome the limitations of specific pre-defined vision tasks. Yet …

Visual segmentation seeks to partition images, video frames, or point clouds into multiple
segments or groups. This technique has numerous real-world applications, such as …

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

Modern video segmentation methods adopt feature transitions between anchor and target
queries to perform cross-frame object association. The smooth feature transitions between …

We present GvSeg, ag eneral v ideo seg mentation framework for addressing four different
video segmentation tasks (ie., instance, semantic, panoptic, and exemplar-guided) while …

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

The pre-trained vision-language model, exemplified by CLIP [1], advances zero-shot
semantic segmentation by aligning visual features with class embeddings through a …

We present the\textbf {D} ecoupled\textbf {VI} deo\textbf {S} egmentation (DVIS) framework, a
novel approach for the challenging task of universal video segmentation, including video …

Abstract Video Temporal Grounding (VTG) aims to ground specific segments within an
untrimmed video corresponding to the given natural language query. Existing VTG methods …

Owing to the advancements in deep learning, object detection has made significant
progress in estimating the positions and classes of multiple objects within an image …