.png){kind=icon}
Return
Query-guided predicate decoupling and prototype approximation learning for scene graph generation
.png){kind=icon}
PRE
AI
DOI：10.1016/j.eswa.2025.129525.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• This work addresses the long-tail distribution problem from both feature decoupling and approximate learning perspectives. • At the feature level, a decoupling method is designed to separate entity and predicate representations. • The homogeneity among same category predicate representations is leveraged to alleviate decision-making pressure at the classification level. • Experiments on multiple datasets demonstrate competitive performance and effectively mitigate the issue of biased predictions.
Journal
IF:
7.5
Papers:
3.0W
Citations:
10.2W
Organization
View more organizations
Cited Papers
.png){kind=icon}
ShareSave
ShareSaveShareSaveShareSave View more