Search Results for author: Markus Woodson

Found 3 papers, 1 papers with code

Long-range Multimodal Pretraining for Movie Understanding

no code implementations ICCV 2023 Dawit Mureja Argaw, Joon-Young Lee, Markus Woodson, In So Kweon, Fabian Caba Heilbron

While great progress has been attained, there is still a need for a pretrained multimodal model that can perform well in the ever-growing set of movie understanding tasks the community has been establishing.

Video-ReTime: Learning Temporally Varying Speediness for Time Remapping

no code implementations11 May 2022 Simon Jenni, Markus Woodson, Fabian Caba Heilbron

Furthermore, we propose an optimization for video re-timing that enables precise control over the target duration and performs more robustly on longer videos than prior methods.

Action Recognition

Cannot find the paper you are looking for? You can Submit a new open access paper.