Certain embodiments involve switching to a particular video loop based on a user's focus while displaying video content to a user. For example, a video playback system identifies a current frame of the video content in a current region of interest being presented to a user on a presentation device. The video playback system also identifies an updated region of interest in the video content. The video playback system determines that a start frame and an end frame of a video portion within the region of interest have a threshold similarity. The video playback system selects, based on the threshold similarity, the video portion as a loop to be displayed to the user in the updated region of interest. The video playback system causes the presentation device to display the video portion as the loop.