Interestingness is defined as the power of engaging and holding the curiosity. While humans can almost effortlessly rank and judge interestingness of a scene, automated prediction of interestingness for an arbitrary scene is a challenging problem. In this work, we attempt to develop a computational model for the said problem. Our approach is based on identifying and extracting context-specific features from video clips. These features are subsequently utilized in a predictor model to provide continuous scores that can be related to the interestingness of the scene in question. Such computational models can be useful in a automated analysis of videos (eg. movie, a CCTV footage or a clip from an advertisement). © 2017 Author/owner(s).