Text-based editing of talking-head video

O Fried, A Tewari, M Zollhöfer, A Finkelstein… - ACM Transactions on …, 2019 - dl.acm.org
Editing talking-head video to change the speech content or to remove filler words is
challenging. We propose a novel method to edit talking-head video based on its transcript to …

PopBlends: Strategies for conceptual blending with large language models

S Wang, S Petridis, T Kwon, X Ma… - Proceedings of the 2023 …, 2023 - dl.acm.org
Pop culture is an important aspect of communication. On social media people often post pop
culture reference images that connect an event, product or other entity to a pop culture …

[PDF][PDF] Write-a-video: computational video montage from themed text.

M Wang, GW Yang, SM Hu, ST Yau… - ACM Trans …, 2019 - cg.cs.tsinghua.edu.cn
Intelligent tools that assist inexperienced users in creative processes are becoming more
abundant: for image editing, for drawing and even for 3D modeling and fabrication. One …

Autonomous aerial cinematography in unstructured environments with learned artistic decision‐making

R Bonatti, W Wang, C Ho, A Ahuja… - Journal of Field …, 2020 - Wiley Online Library
Aerial cinematography is revolutionizing industries that require live and dynamic camera
viewpoints such as entertainment, sports, and security. However, safely piloting a drone …

The anatomy of video editing: A dataset and benchmark suite for ai-assisted video editing

DM Argaw, FC Heilbron, JY Lee, M Woodson… - … on Computer Vision, 2022 - Springer
Abstract Machine learning is transforming the video editing industry. Recent advances in
computer vision have leveled-up video editing tasks such as intelligent reframing …

Rescribe: Authoring and automatically editing audio descriptions

A Pavel, G Reyes, JP Bigham - Proceedings of the 33rd Annual ACM …, 2020 - dl.acm.org
Audio descriptions make videos accessible to those who cannot see them by describing
visual content in audio. Producing audio descriptions is challenging due to the synchronous …

Rekall: Specifying video events using compositions of spatiotemporal labels

DY Fu, W Crichton, J Hong, X Yao, H Zhang… - arXiv preprint arXiv …, 2019 - arxiv.org
Many real-world video analysis applications require the ability to identify domain-specific
events in video, such as interviews and commercials in TV news broadcasts, or action …

Can a robot become a movie director? learning artistic principles for aerial cinematography

M Gschwindt, E Camci, R Bonatti… - 2019 IEEE/RSJ …, 2019 - ieeexplore.ieee.org
Aerial filming is constantly gaining importance due to the recent advances in drone
technology. It invites many intriguing, unsolved problems at the intersection of aesthetical …

Visual rhythm and beat

A Davis, M Agrawala - ACM Transactions on Graphics (TOG), 2018 - dl.acm.org
We present a visual analogue for musical rhythm derived from an analysis of motion in
video, and show that alignment of visual rhythm with its musical counterpart results in the …

Crosscast: adding visuals to audio travel podcasts

H Xia, J Jacobs, M Agrawala - Proceedings of the 33rd annual ACM …, 2020 - dl.acm.org
Audio travel podcasts are a valuable source of information for travelers. Yet, travel is, in
many ways, a visual experience and the lack of visuals in travel podcasts can make it difficult …