Abstract: With the rapid development of intelligent surveillance technology, the massive amount of multimodal data (e.g., videos, images, and text) has imposed higher demands on efficient information ...

Abstract: Recent CLIP-guided 3D generation methods have achieved promising results but struggle with generating faithful 3D shapes that conform with input text due to the gap between text and image ...

TL;DR: We propose ReAlign, a plug-and-play reward-guided alignment strategy for text-to-motion generation, which explicitly enhances both semantic consistency and motion realism throughout the ...