MoCLIP: Motion-Aware Fine-Tuning and Distillation of CLIP for Human

编辑：广东客   |   分类：CV   |  

Note: We don't have the ability to review paper

PubDate: May 2025

Teams:University of North Carolina at Charlotte

Writers:Gabriel Maldonado Armin Danesh Pazho Ghazal Alinezhad Noghre Vinit Katariya Hamed Tabkhi

PDF:MoCLIP: Motion-Aware Fine-Tuning and Distillation of CLIP for Human

Abstract

Human motion generation is essential for fields such as animation, robotics, and virtual reality, requiring models that effectively capture motion dynamics from text descriptions. Existing approaches often rely on Contrastive Language-Image Pretraining (CLIP)-based text encoders, but their training on text-image pairs constrains their ability to understand temporal and kinematic structures inherent in motion and motion generation. This work introduces MoCLIP, a fine-tuned CLIP model with an additional motion encoding head, trained on motion sequences using contrastive learning and tethering loss. By explicitly incorporating motion-aware representations, MoCLIP
enhances motion fidelity while remaining compatible with existing CLIP-based pipelines and seamlessly integrating into various CLIP-based methods. Experiments demonstrate that MoCLIP improves Top-1, Top-2, and Top-3 accuracy while maintaining competitive FID, leading to improved text-to-motion alignment results. These results highlight MoCLIP’s versatility and effectiveness, establishing it as a robust framework for enhancing motion generation.
本文链接：https://paper.nweon.com/16460

您可能还喜欢...

Paper