Practitioner’s Takeaway • Our eight guidelines support practitioners in producing taskpertinent video tutorials for software training. • Our eight guidelines have been tested and proven effective under controlled, experimental conditions • e descriptions that accompany the eight guidelines for the design of video instructions provide practitioners with Purpose: Video has become a popular means ...

In this work we discuss an emotional classification of videos based on users physiological signals and video low-level processing. This kind of automatic user classification has the potential to increase the naturalness of interaction. Everyday the number of online videos and films is increasingly available. The emotional dimensions of videos require specific tools to enable video access and se...

Background: Respiratory function in patients undergoing open heart surgery is disrupted after surgery.  Patient education on managing complications can reduce occurrence or severity of them. A variety of educational tools has been introduced, but there are controversies about the most appropriate tools. Aim: Determine the effect of instructional videos on respiratory function of the patients af...

BACKGROUND We developed a novel artificial simulator for endoscopic submucosal dissection (ESD) as a bridge between instructional videos and animal tissue training and aimed to evaluate the feasibility of using an artificial tissue model in ESD training. METHODS Eight gastroenterology fellows from one medical center were enrolled in this ESD training program. Before and after the simulator tr...

In this paper, a novel efficient algorithm is presented for locating and tracking object parts in low resolution videos using Lowe’s SIFT keypoints with a nearest neighbor object detection approach. Our interest lies in using this information as one step in the process of automatically programming service, household, or personal robots to perform the skills that are being taught in easily obtai...

This paper presents a new method for unsupervised segmentation of complex activities from video into multiple steps, or sub-activities, without any textual input. We propose an iterative discriminative-generative approach which alternates between discriminatively learning the appearance of sub-activities from the videos’ visual features to sub-activity labels and generatively modelling the temp...