Abstract: Learning to build 3D scene graphs is essential for real-world perception in a structured and rich fashion. However, previous 3D scene graph generation methods utilize a fully supervised ...

This Java project provides a powerful workflow engine and a user-friendly visual editor. The workflow engine allows users to define, execute, and manage complex business processes, while the visual ...

Abstract: Large Vision-Language Models have drawn much attention and become increasingly applicable in complicated multimodal tasks such as visual question answering, video grounding, etc. However, it ...

MSVMamba is a visual state space model that introduces a hierarchy in hierarchy design to the VMamba model. This repository contains the code for training and evaluating MSVMamba models on the ...