Video summarization model based on multi-scale temporal modeling and dynamic spatial feature fusion
Image Processing|更新时间:2025-12-12
|
Video summarization model based on multi-scale temporal modeling and dynamic spatial feature fusion
“In the field of video summarization, researchers have proposed a new model that effectively improves the accuracy and effectiveness of video summarization through multi-scale time shift and deformable local attention mechanism.”
Chinese Journal of Liquid Crystals and DisplaysVol. 40, Issue 11, Pages: 1729-1743(2025)
作者机构:
北京建筑大学 智能科学与技术学院,北京 102616
作者简介:
基金信息:
Computer Foundation Education Teaching Research Project of Association of Fundamental Computing Education in Chinese Universities(2020-AFCEC-162;2020-AFCEC-006)
LI Zehui, ZHANG Lin, SHAN Xianying, et al. Video summarization model based on multi-scale temporal modeling and dynamic spatial feature fusion[J]. Chinese Journal of Liquid Crystals and Displays, 2025, 40(11): 1729-1743.
DOI:
LI Zehui, ZHANG Lin, SHAN Xianying, et al. Video summarization model based on multi-scale temporal modeling and dynamic spatial feature fusion[J]. Chinese Journal of Liquid Crystals and Displays, 2025, 40(11): 1729-1743. DOI: 10.37188/CJLCD.2025-0189. CSTR: 32172.14.CJLCD.2025-0189.
Video summarization model based on multi-scale temporal modeling and dynamic spatial feature fusion