About The Forum
Calendar 2017 Poster Sessions : Computational Video Editing for Dialogue-Driven Scenes
Abstract:
Often editing even short videos can be a time-consuming and labor-intensive process. In order to reduce the time to edit videos, we present a system for efficiently editing a specific, common type of scene: dialogue-driven scenes. The input to our system is a standard film script and multiple video takes, each capturing a different camera framing or performance of the complete scene. Our system then automatically selects the most appropriate clip from one of the input takes, for each line of dialogue, based on a user-specified set of film-editing idioms, i.e., common conventions utilized by professional video editors. Our system produces edits significantly faster than conventional editing tools, and it allows users to iteratively explore the space of edit designs.
Bios:
Mackenzie Leake is a PhD student in the computer science department at Stanford University. She is advised by Maneesh Agrawala and is a member of the Stanford Graphics and Human-Computer Interaction groups. She has a B.A. in computational science and studio art from Scripps College and is supported by Brown Institute for Media Innovation and Adobe Research fellowships.
Abe Davis is a new postdoc at Stanford working with Doug James and Maneesh Agrawala. He recently completed his PhD at MIT, where he was advised by Fredo Durand. His thesis focused on analyzing subtle variations in video to reason about physical vibrations. Abe has explored applications of his work in graphics, vision, and civil engineering, with publications in SIGGRAPH, SIGGRAPH Asia, and CVPR, as well as top venues in structural health monitoring and nondestructive testing. His dissertation won the 2016 MIT Sprowls award for outstanding thesis in computer science. Abe's research has been featured in most major news outlets that cover science and technology. Business Insider named him one of the "8 most innovative scientists in tech and engineering" in 2015, and Forbes named him one of their "30 under 30" in 2016.
Often editing even short videos can be a time-consuming and labor-intensive process. In order to reduce the time to edit videos, we present a system for efficiently editing a specific, common type of scene: dialogue-driven scenes. The input to our system is a standard film script and multiple video takes, each capturing a different camera framing or performance of the complete scene. Our system then automatically selects the most appropriate clip from one of the input takes, for each line of dialogue, based on a user-specified set of film-editing idioms, i.e., common conventions utilized by professional video editors. Our system produces edits significantly faster than conventional editing tools, and it allows users to iteratively explore the space of edit designs.
Bios:
Mackenzie Leake is a PhD student in the computer science department at Stanford University. She is advised by Maneesh Agrawala and is a member of the Stanford Graphics and Human-Computer Interaction groups. She has a B.A. in computational science and studio art from Scripps College and is supported by Brown Institute for Media Innovation and Adobe Research fellowships.
Abe Davis is a new postdoc at Stanford working with Doug James and Maneesh Agrawala. He recently completed his PhD at MIT, where he was advised by Fredo Durand. His thesis focused on analyzing subtle variations in video to reason about physical vibrations. Abe has explored applications of his work in graphics, vision, and civil engineering, with publications in SIGGRAPH, SIGGRAPH Asia, and CVPR, as well as top venues in structural health monitoring and nondestructive testing. His dissertation won the 2016 MIT Sprowls award for outstanding thesis in computer science. Abe's research has been featured in most major news outlets that cover science and technology. Business Insider named him one of the "8 most innovative scientists in tech and engineering" in 2015, and Forbes named him one of their "30 under 30" in 2016.