A method includes obtaining a stream of radar data into a sliding input data window composed of recent radar frames from the stream. Each radar frame within the data window includes features selected from a predefined feature set and at least one of time-velocity data or time angle data. The method includes, for each radar frame within the data window, receiving a binary prediction indicating whether the radar frame includes a gesture end. The method includes in response to the binary prediction indicating that the radar frame includes the gesture end, triggering an early stop (ES) checker to determine whether an ES condition is satisfied. Determining whether the ES condition is satisfied comprises determining whether a noise frames condition and a valid activity condition are satisfied. The method includes in response to a determination that the ES condition is satisfied, triggering a gesture classifier to predict a gesture type.