Text-to-Motion Retrieval: Towards Joint Understanding of Human Motion Data and Natural Language
This work addresses the challenge of efficiently accessing large volumes of human motion data for applications in fields like robotics and animation, though it is incremental as it builds on existing text-to-image/video matching techniques.
The paper tackles the problem of retrieving human motion data based on natural language descriptions by proposing a text-to-motion retrieval task and introducing a transformer-based method called Motion Transformer (MoT) with divided space-time attention, achieving competitive results on datasets like KIT Motion-Language and HumanML3D.
Due to recent advances in pose-estimation methods, human motion can be extracted from a common video in the form of 3D skeleton sequences. Despite wonderful application opportunities, effective and efficient content-based access to large volumes of such spatio-temporal skeleton data still remains a challenging problem. In this paper, we propose a novel content-based text-to-motion retrieval task, which aims at retrieving relevant motions based on a specified natural-language textual description. To define baselines for this uncharted task, we employ the BERT and CLIP language representations to encode the text modality and successful spatio-temporal models to encode the motion modality. We additionally introduce our transformer-based approach, called Motion Transformer (MoT), which employs divided space-time attention to effectively aggregate the different skeleton joints in space and time. Inspired by the recent progress in text-to-image/video matching, we experiment with two widely-adopted metric-learning loss functions. Finally, we set up a common evaluation protocol by defining qualitative metrics for assessing the quality of the retrieved motions, targeting the two recently-introduced KIT Motion-Language and HumanML3D datasets. The code for reproducing our results is available at https://github.com/mesnico/text-to-motion-retrieval.