Publications

@inproceedings{2022-Chi-SVPFD,

title = {Synthesis-Assisted Video Prototyping From a Document},

author = {Peggy Chi and Tao Dong and Christian Frueh and Brian Colonna and Vivek Kwatra and Irfan Essa},

url = {https://research.google/pubs/pub51631/

https://dl.acm.org/doi/abs/10.1145/3526113.3545676},

doi = {10.1145/3526113.3545676},

year  = {2022},

date = {2022-10-01},

urldate = {2022-10-01},

booktitle = {Proceedings of the 35th Annual ACM Symposium on User Interface Software and Technology},

pages = {1--10},

abstract = {Video productions commonly start with a script, especially for talking head videos that feature a speaker narrating to the camera. When the source materials come from a written document -- such as a web tutorial, it takes iterations to refine content from a text article to a spoken dialogue, while considering visual compositions in each scene. We propose Doc2Video, a video prototyping approach that converts a document to interactive scripting with a preview of synthetic talking head videos. Our pipeline decomposes a source document into a series of scenes, each automatically creating a synthesized video of a virtual instructor. Designed for a specific domain -- programming cookbooks, we apply visual elements from the source document, such as a keyword, a code snippet or a screenshot, in suitable layouts. Users edit narration sentences, break or combine sections, and modify visuals to prototype a video in our Editing UI. We evaluated our pipeline with public programming cookbooks. Feedback from professional creators shows that our method provided a reasonable starting point to engage them in interactive scripting for a narrated instructional video.},

keywords = {computational video, generative media, google, human-computer interaction, UIST, video editing},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{2021-Frey-ASTNVE,

title = {Automatic Style Transfer for Non-Linear Video Editing},

author = {Nathan Frey and Peggy Chi and Weilong Yang and Irfan Essa},

url = {https://arxiv.org/abs/2105.06988

https://research.google/pubs/pub50449/},

doi = {10.48550/arXiv.2105.06988},

year  = {2021},

date = {2021-06-01},

urldate = {2021-06-01},

booktitle = {Proceedings of CVPR Workshop on AI for Content Creation (AICC)},

keywords = {computational video, CVPR, google, video editing},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{2020-Chi-AVCFP,

title = {Automatic Video Creation From a Web Page},

author = {Peggy Chi and Zheng Sun and Katrina Panovich and Irfan Essa},

url = {https://dl.acm.org/doi/abs/10.1145/3379337.3415814

https://research.google/pubs/pub49618/

https://ai.googleblog.com/2020/10/experimenting-with-automatic-video.html

https://www.youtube.com/watch?v=3yFYc-Wet8k},

doi = {10.1145/3379337.3415814},

year  = {2020},

date = {2020-10-01},

urldate = {2020-10-01},

booktitle = {Proceedings of the 33rd Annual ACM Symposium on User Interface Software and Technology},

pages = {279--292},

organization = {ACM CHI},

abstract = {Creating marketing videos from scratch can be challenging, especially when designing for multiple platforms with different viewing criteria. We present URL2Video, an automatic approach that converts a web page into a short video given temporal and visual constraints. URL2Video captures quality materials and design styles extracted from a web page, including fonts, colors, and layouts. Using constraint programming, URL2Video's design engine organizes the visual assets into a sequence of shots and renders to a video with user-specified aspect ratio and duration. Creators can review the video composition, modify constraints, and generate video variation through a user interface. We learned the design process from designers and compared our automatically generated results with their creation through interviews and an online survey. The evaluation shows that URL2Video effectively extracted design elements from a web page and supported designers by bootstrapping the video creation process.},

keywords = {computational video, google, human-computer interaction, UIST, video editing},

pubstate = {published},

tppubtype = {inproceedings}

}