Classifies physical activities in real time from wearable motion sensor data.

Transcribes spoken audio into text using the Whisper speech recognition model, optimized for edge inference.

Detects products in smart vending environments to support automated product recognition and inventory workflows.

Segments foreground objects from image backgrounds to support automated industrial vision and inspection workflows.

Detects and maps land-cover changes from multi-temporal satellite or aerial imagery for environmental monitoring and urban analysis.