To understand the real world using various types of data, Artificial Intelligence (AI) is the
most used technique nowadays. While finding the pattern within the analyzed data …

Modern autonomous driving system is characterized as modular tasks in sequential order,
ie, perception, prediction, and planning. In order to perform a wide diversity of tasks and …

Grid-centric perception is a crucial field for mobile robot perception and navigation.
Nonetheless, grid-centric perception is less prevalent than object-centric perception for …

Training data for video segmentation are expensive to annotate. This impedes extensions of
end-to-end algorithms to new video segmentation tasks, especially in large-vocabulary …

For the last few decades, several major subfields of artificial intelligence including computer
vision, graphics, and robotics have progressed largely independently from each other …

Video object segmentation (VOS) aims at segmenting a particular object throughout the
entire video clip sequence. The state-of-the-art VOS methods have achieved excellent …

Panoptic segmentation assigns semantic and instance ID labels to every pixel of an image.
As permutations of instance IDs are also valid solutions, the task requires learning of high …

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 …

Many existing autonomous driving paradigms involve a multi-stage discrete pipeline of
tasks. To better predict the control signals and enhance user safety, an end-to-end approach …

This work presents a simple vision transformer design as a strong baseline for object
localization and instance segmentation tasks. Transformers recently demonstrate …