XRFv2 Plus: Multimodal Human Activity Data with WiFi, IMU, and Visual Sensors

Multimodal sensor data includes WiFi signals, inertial measurement units, AirPods audio, depth/IR cameras, DensePose, human pose, mesh, and action labels. The dataset appears to be designed for complex human activity analysis and sensor fusion tasks. Its origin, size, and collection methodology are not specified in the available metadata.

Use Cases

• Train human action recognition models based on the provided action labels.
• Develop sensor fusion algorithms based on the combination of WiFi, IMU, and visual data.
• Research human pose and mesh estimation based on the DensePose and pose data.
• Explore audio-visual context modeling based on the AirPods and depth/IR sensor streams.

Strengths

• Includes a diverse set of sensor modalities such as WiFi, IMU, audio, and visual data.
• Contains high-level annotations like DensePose, human mesh, and action labels.

Limitations

• Row count is unknown, which may limit suitability assessment.
• Column-level documentation is absent; field semantics must be inferred after download.
• Last update date is unknown; freshness unverified.