Find the Cliffhanger: Multi-Modal Trailerness in Soap Operas

Creating a trailer requires carefully picking out and piecing together briefenticing moments out of a longer video, making it a chal- lenging andtime-consuming task. This requires selecting moments based on both visual anddialogue information. We introduce a multi-modal method for predicting thetrailerness to assist editors in selecting trailer- worthy moments fromlong-form videos. We present results on a newly introduced soap opera dataset,demonstrating that predicting trailerness is a challenging task that benefitsfrom multi-modal information. Code is available athttps://github.com/carlobretti/cliffhanger