AnyMo uses physics-grounded IMU simulation over dense body placements, graph encoder pre-training, and LLM alignment to enable setup-agnostic motion modeling, reporting gains on zero-shot HAR, retrieval, and captioning across datasets.
Crosshar: Generalizing cross-dataset human activity recognition via hierarchical self-supervised pretraining.Proc
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
GenHAR generalizes cross-domain human activity recognition by 9.97% accuracy and 6.4x lower FLOPs via tokenized sensor data, frequency channel correlations, selective masking, and efficient attention, with deployment detecting 2.15 billion activities.
citing papers explorer
-
AnyMo: Geometry-Aware Setup-Agnostic Modeling of Human Motion in the Wild
AnyMo uses physics-grounded IMU simulation over dense body placements, graph encoder pre-training, and LLM alignment to enable setup-agnostic motion modeling, reporting gains on zero-shot HAR, retrieval, and captioning across datasets.
-
GenHAR: Generalizing Cross-domain Human Activity Recognition for Last-mile Delivery
GenHAR generalizes cross-domain human activity recognition by 9.97% accuracy and 6.4x lower FLOPs via tokenized sensor data, frequency channel correlations, selective masking, and efficient attention, with deployment detecting 2.15 billion activities.