Replication Data for: Eat-Radar: Continuous Fine-Grained Eating Gesture Detection Using FMCW Radar and 3D Temporal Convolutional Network With Attention

The FMCW radar-based food intake monitoring-oriented dataset contains 70 meal sessions (4132 eating gestures and 893 drinking gestures) from 70 participants with a total duration of 1155 minutes. Four eating styles (fork & knife, chopsticks, spoon, hand) are included in this dataset. The radar data formats in this dataset include Range-Doppler-Time data (RD Cube), and Doppler-Time data (DT Map).