In the field of visual scene understanding, deep neural networks have made impressive
advancements in various core tasks like segmentation, tracking, and detection. However …

As the most fundamental scene understanding tasks, object detection and segmentation
have made tremendous progress in deep learning era. Due to the expensive manual …

Despite the recent advances in unified image segmentation (IS) develo** a unified video
segmentation (VS) model remains a challenge. This is mainly because generic category …

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 …

Multimodal fusion, leveraging data like vision and language, is rapidly gaining traction. This
enriched data representation improves performance across various tasks. Existing methods …

Panoramic videos contain richer spatial information and have attracted tremendous amounts
of attention due to their exceptional experience in some fields such as autonomous driving …

Abstract Video Object Segmentation (VOS) is crucial for several applications, from video
editing to video data generation. Training a VOS model requires an abundance of manually …

Multi-modal Video Object Segmentation (VOS), including RGB-Thermal, RGB-Depth, and
RGB-Event, has garnered attention due to its capability to address challenging scenarios …

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 studies indicate that sparse attacks threaten the security of deep learning models,
which modify only a small set of pixels in the input based on the l0 norm constraint. While …