Video Browsing by Direct Manipulation

AbstractWe present a method for browsing videos by directly dragging their content. This method brings the benefits of direct manipulation to an activity typically mediated by widgets. We support this new type of interactivity by: 1) automatically extracting motion data from videos; and 2) a new technique called relative flow dragging that lets users control video playback by moving objects of interest along their visual trajectory. We show that this method can out-perform the traditional seeker bar in video browsing tasks that focus on visual content rather than time.

Download publication

Associated Researchers

Pierre Dragicevic

University of Toronto

Gonzalo Ramos

University of Toronto

Derek Nowrouzezahrai

University of Toronto

Ravin Balakrishnan

University of Toronto

Karan Singh

University of Toronto

View all researchers

Related Resources

See what’s new.



Language Model Crossover: Variation through Few-Shot Prompting

Pursuing the insight that language models naturally enable an…



Effects of Team Size on Participation, Awareness, and Technology Choice in Geographically Distributed Teams

In this paper we investigate the effects that team size has on…



A Design Environment for the Rapid Specification and Fabrication of Printable Robots

In this work, we have developed a design environment to allow casual…



PenLight: Combining a Mobile Projector and a Digital Pen for Dynamic Visual Overlay

Digital pen systems, originally designed to digitize annotations made…

Get in touch

Something pique your interest? Get in touch if you’d like to learn more about Autodesk Research, our projects, people, and potential collaboration opportunities.

Contact us