Sagie Benaim
Inbar Mosseri
SpeedNet: Learning the Speediness in Videos
Given an input video, our method automatically predicts the "speediness" of objects in the video-—whether they move faster, at, or slower than their natural speed. Right: a video of a dancer alternates between normal speed and slow motion play-back, as correctly captured by our speediness prediction over time. The core component of our method is SpeedNet (left)-—a novel deep network that can detect whether an object is moving at, or faster than, its normal speed.
We wish to automatically predict the "speediness" of moving objects in videos---whether they move faster, at, or slower than their "natural" speed. The core component in our approach is SpeedNet---a novel deep network trained to detect if a video is playing at normal rate, or if it is sped up. SpeedNet is trained on a large corpus of natural videos in a self-supervised manner, without requiring any manual annotations. We show how this single, binary classification network can be used to detect arbitrary rat
Sagie Benaim
Inbar Mosseri