SkeletonLLM translates skeleton kinematics into compact image sequences via an end-to-end differentiable renderer DrAction and uses cooperative training to enable MLLMs to perform open-vocabulary action recognition, motion captioning, and QA across heterogeneous skeleton formats.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Universal Skeleton Understanding via Differentiable Rendering and MLLMs
SkeletonLLM translates skeleton kinematics into compact image sequences via an end-to-end differentiable renderer DrAction and uses cooperative training to enable MLLMs to perform open-vocabulary action recognition, motion captioning, and QA across heterogeneous skeleton formats.