.png){kind=icon}
.png){kind=icon}
Return
HiTIMI: Hierarchical type-driven inter-modality interaction framework for multimodal named entity recognition
.png){kind=icon}
PRE
AI
DOI：10.1016/j.neucom.2025.132131.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• Enhanced predefined entity types as key guiding cues to ensure semantic consistency. • Hierarchical interactions enhance the fine-grained understanding of diverse inputs. • Type-driven unimodal auxiliary tasks are designed as additional supervision signals.
Journal
IF:
6.5
Papers:
2.5W
Citations:
6.5W