SATO: Stable Text-to-Motion Framework

arXiv:2405.01461v1 Announce Type: new
Abstract: Is the Text to Motion model robust? Recent advancements in Text to Motion models primarily stem from more accurate predictions of specific actions. However, the text modality typically relies solely on pre-trained Contrastive Language-Image Pretraining (CLIP) models. Our research has uncovered a significant issue with the text-to-motion model: its predictions often exhibit inconsistent outputs, resulting in vastly different or even incorrect poses when presented with semantically similar or identical text inputs. In this paper, we …

abstract arxiv clip cs.cv framework however image issue language predictions pretraining research robust stem text type