AnyMo is a masked-modeling framework for any-modality human motion generation trained on the new OmniHuMo dataset of 5,000+ hours of multimodal motion sequences.
Rtmw: Real-time multi-person 2d and 3d whole-body pose estimation
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.CV 3years
2026 3representative citing papers
A single-camera pipeline estimates human awareness of AMRs via 3D pose lifting and head orientation to allow adaptive robot motion in mixed human-robot warehouses.
citing papers explorer
-
AnyMo: Scaling Any-Modality Conditional Motion Generation with Masked Modeling
AnyMo is a masked-modeling framework for any-modality human motion generation trained on the new OmniHuMo dataset of 5,000+ hours of multimodal motion sequences.
-
Vision-Based Human Awareness Estimation for Enhanced Safety and Efficiency of AMRs in Industrial Warehouses
A single-camera pipeline estimates human awareness of AMRs via 3D pose lifting and head orientation to allow adaptive robot motion in mixed human-robot warehouses.
- DanceHMR: Hand-Aware Whole-Body Human Mesh Recovery from Monocular Videos