English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

In this paper, we present TMR, a simple yet effective approach for text to 3Dhuman motion retrieval. While previous work has only treated retrieval as aproxy evaluation metric, we tackle it as a standalone task. Our method extendsthe state-of-the-art text-to-motion synthesis model TEMOS, and incorporates acontrastive loss to better structure the cross-modal latent space. We show thatmaintaining the motion generation loss, along with the contrastive training, iscrucial to obtain good performance. We introduce a benchmark for evaluation andprovide an in-depth analysis by reporting results on several protocols. Ourextensive experiments on the KIT-ML and HumanML3D datasets show that TMRoutperforms the prior work by a significant margin, for example reducing themedian rank from 54 to 19. Finally, we showcase the potential of our approachon moment retrieval. Our code and models are publicly available athttps://mathis.petrovich.fr/tmr.

TMR: Text-to-Motion Retrieval Using Contrastive 3D Human Motion Synthesis