Motion-to-Attention: Enhancing Attention Maps to Improve Performance of Text-Guided Video Editing
ACM Transactions on Multimedia Computing, Communications, and Applications · 30.06.2026 · 22 (6) · 1-23
DOI: 10.1145/3816727 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Transactions on Multimedia Computing, Communications, and Applications, online erschienen am 08.06.2026. Verfasst von Seong-Hun Jeong und 4 weiteren Autor:innen. Die Arbeit nennt 48 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Research Foundation of Korea, Government of the Republic of Korea, Regional Innovation System and Education.
Abstract (Originalsprache)
Recent research in text-guided video editing aims to extend image-based editing models to video domains. A significant challenge in this transition is ensuring temporal consistency across frames. However, existing methods often exhibit limited editing accuracy when processing prompts associated with motion, such as “ floating ” or “ moving .” Our analysis indicates that this limitation arises from inaccurate attention maps corresponding to motion-related prompts. To address this, we introduce the Motion-to-Attention (M2A) module, explicitly integrating motion information for enhanced video editing precision. Specifically, we first convert optical flow extracted from the video into a comprehensive motion map. Optionally, users can specify directional information to refine motion map extraction further. The proposed M2A module incorporates two complementary techniques: “ Attention–Motion Swap ,” which directly substitutes the imprecise attention map of motion prompts with the extracted motion map, and “ Attention–Motion Fusion ,” which adaptively enhances attention maps based on the correlation with the motion map using a carefully selected Fusion metric. Experimental validation demonstrates that incorporating our M2A module into existing text-to-video editing frameworks significantly improves both quantitative performance metrics (CLIP-Acc, Masked PSNR, BRISQUE) and qualitative visual quality. Extensive experiments and comparative studies confirm the superior editability and robustness of our method over current state-of-the-art approaches. Comprehensive results are publicly available at https://currycurry915.github.io/Motion-to-Attention/ .
Förderung
- National Research Foundation of Korea
- Government of the Republic of Korea
- Regional Innovation System and Education
Zitieren
APA
Jeong, S., Jin, I., Choo, H., Na, H., & Kong, K. (2026). Motion-to-Attention: Enhancing Attention Maps to Improve Performance of Text-Guided Video Editing. ACM Transactions on Multimedia Computing, Communications, and Applications, 22(6), 1-23. https://doi.org/10.1145/3816727
Vancouver
Jeong S, Jin I, Choo H, Na H, Kong K. Motion-to-Attention: Enhancing Attention Maps to Improve Performance of Text-Guided Video Editing. ACM Transactions on Multimedia Computing, Communications, and Applications. 2026;22(6):1-23. doi:10.1145/3816727
BibTeX
@article{Jeong2026,
author = {Jeong, Seong-Hun and Jin, In-Hwan and Choo, Haesoo and Na, Hyeonjun and Kong, Kyeongbo},
title = {Motion-to-Attention: Enhancing Attention Maps to Improve Performance of Text-Guided Video Editing},
journal = {ACM Transactions on Multimedia Computing, Communications, and Applications},
year = {2026},
volume = {22},
number = {6},
pages = {1--23},
doi = {10.1145/3816727}
}
EUVIMED