Motion-Adapter improves text-to-motion diffusion models for compound actions by using decoupled cross-attention maps as structural masks during denoising to produce more coherent full-body motions.
Spatial temporal graph convolutional networks for skeleton-based action recognition
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
Higher temporal resolution in video significantly improves zero-shot semantic understanding of high-speed human actions like kendo.
SASI combines skeleton-based graph convolutions with sub-action semantics for improved early action recognition on the BABEL dataset.
citing papers explorer
-
Motion-Adapter: A Diffusion Model Adapter for Text-to-Motion Generation of Compound Actions
Motion-Adapter improves text-to-motion diffusion models for compound actions by using decoupled cross-attention maps as structural masks during denoising to produce more coherent full-body motions.
-
High-Speed Vision Improves Zero-Shot Semantic Understanding of Human Actions
Higher temporal resolution in video significantly improves zero-shot semantic understanding of high-speed human actions like kendo.
-
SASI: Leveraging Sub-Action Semantics for Robust Early Action Recognition in Human-Robot Interaction
SASI combines skeleton-based graph convolutions with sub-action semantics for improved early action recognition on the BABEL dataset.