ContainersNVIDIADeepSeek-R1NVIDIALlama-3.1-Nemotron-70B-InstructNVIDIAPyTorch
CollectionsNVIDIAOmniverse Kit (FB)NVIDIADeepStream SDKNVIDIAOmniverse Kit App Streaming
ModelsNVIDIAStyleGAN3 pretrained modelsNVIDIAPeopleNetNVIDIATrafficCamNet
ResourcesNVIDIARiva Skills Quick Start
Helm ChartsNVIDIAGPU OperatorNVIDIANVIDIA NIM Operator
NVIDIA
NVIDIA
Pose Classification
Model
NVIDIA
NVIDIA
Pose Classification

Pose classification network to classify poses of people from their skeletons.

This model is backed by NVIDIA's Plus Plus (++) Promise
to learn more about the quality of the datasets used to train this model.
FieldResponse
Intended Application(s) & Domain(s):Classifies human body poses.
Model Type:Pose Classification
Intended Users:Developers working in industrial, personal health, and smart spaces applications.
Output:Category Label(s)
Describe how the model works:Classifies poses of people from their skeletons: sitting down, getting up, sitting, standing, walking, jumping
Technical Limitations:PoseClassificationNet does not give good results for very crowded scenes, especially if detecting the pose for small-scale people in the image. PoseClassificationNet may also have difficulty estimating poses of people who are occluded by other objects or persons or in environments where there is no distinction between the person and the background.
Verified to have met prescribed NVIDIA standards:Yes
Performance Metrics:Accuracy, Precision, Recall
Potential Known Risks:Model may fail to classify correct pose.
Licensing:https://www.nvidia.com/en-us/data-center/products/nvidia-ai-enterprise/eula/