The early stages of video editing present many cognitively demanding tasks that require editors to remember and structure large amounts of video. In our formative work we learned that editors break down the editing process into smaller parts by labeling and organizing footage around central themes. Using current video editing tools, this process is slow and largely manual. We present a system called ChunkyEdit for helping editors group video interview clips into thematically coherent chunks, which can then be exported to existing video editing tools and composed into an edited narrative. By focusing on this intermediate step, we leverage computation to do tedious organizational tasks, while preserving the editor's ability to control the primary storytelling decisions. We explore four different topic modeling approaches to creating video chunks. We then evaluate our tool with eight professional video editors to learn how a chunking-based approach could be incorporated into video editing workflows.
https://doi.org/10.1145/3613904.3642667
The ACM CHI Conference on Human Factors in Computing Systems (https://chi2024.acm.org/)