We consider the task of identifying human actions visible in online videos. We focus on the widely spread genre of lifestyle vlogs, which consist of videos of people performing actions while verbally describing them. Our goal is to identify if actions mentioned in the speech description of a video are visually present.
We introduce a novel dataset, IfAct, consisting of 1,268 short video clips paired with sets of actions mentioned in the video transcripts, as well as manual annotations of whether the actions are visible or not. The dataset includes a total of 14,769 actions, 4,340 of which are visible.
Paper | Code | Results | Date | Stars |
---|