.png){kind=icon}
.png){kind=icon}
Return
Domain adaptive video summarization using generalized transformer
.png){kind=icon}
PRE
AI
DOI：10.1016/j.patcog.2025.112059.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• Two-stage domain adaptation framework for cross-domain video summarization. • Regularized feature encoder based on Transformer boosts cross-domain generalization. • Discrepancy reduction loss with confidence weighting adapts to target domain. • Our method outperforms state-of-the-art methods on various datasets and metrics.
Journal
IF:
7.6
Papers:
1.3W
Citations:
4.5W
Organization
No organization information available