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

We introduce Action-GPT, a plug-and-play framework for incorporating LargeLanguage Models (LLMs) into text-based action generation models. Action phrasesin current motion capture datasets contain minimal and to-the-pointinformation. By carefully crafting prompts for LLMs, we generate richer andfine-grained descriptions of the action. We show that utilizing these detaileddescriptions instead of the original action phrases leads to better alignmentof text and motion spaces. We introduce a generic approach compatible withstochastic (e.g. VAE-based) and deterministic (e.g. MotionCLIP) text-to-motionmodels. In addition, the approach enables multiple text descriptions to beutilized. Our experiments show (i) noticeable qualitative and quantitativeimprovement in the quality of synthesized motions, (ii) benefits of utilizingmultiple LLM-generated descriptions, (iii) suitability of the prompt function,and (iv) zero-shot generation capabilities of the proposed approach. Projectpage: https://actiongpt.github.io

Action-GPT: Leveraging Large-scale Language Models for Improved and Generalized Action Generation