Amateur instructional videos often show a single uninterrupted take of a recorded demonstration without any edits. While easy to produce, such videos are often too long as they include unnecessary or repetitive actions as well as mistakes. We introduce DemoCut, a semi-automatic video editing system that improves the quality of amateur instructional videos for physical tasks. DemoCut asks users to mark key moments in a recorded demonstration using a set of marker types derived from our formative study. Based on these markers, the system uses audio and video analysis to automatically organize the video into meaningful segments and apply appropriate video editing effects. To understand the effectiveness of DemoCut, we report a technical evaluation of seven video tutorials created with DemoCut. In a separate user evaluation, all eight participants successfully created a complete tutorial with a variety of video editing effects using our system.
is is a shirt" "Change the color of the shirt" a b c Figure 1. With PIXELTONE, users speak to edit their images instead of hunting through menus. a) The user selects the person's shirt and says "This is a shirt." PIXELTONE associates the tag "shirt" with the selected region. b) The user tells PIXELTONE to "Change the color of the shirt," and c) PIXELTONE applies a hue adjustment to the image and offers a slider so that the user can explore different colors. ABSTRACTPhoto editing can be a challenging task, and it becomes even more difficult on the small, portable screens of mobile devices that are now frequently used to capture and edit images. To address this problem we present PIXELTONE, a multimodal photo editing interface that combines speech and direct manipulation. We observe existing image editing practices and derive a set of principles that guide our design. In particular, we use natural language for expressing desired changes to an image, and sketching to localize these changes to specific regions. To support the language commonly used in photoediting we develop a customized natural language interpreter that maps user phrases to specific image processing operations. Finally, we perform a user study that evaluates and demonstrates the effectiveness of our interface.
No abstract
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with đź’™ for researchers
Part of the Research Solutions Family.