多模态信息融合

M2I2HA: Multi-modal Object Detection Based on Intra- and Inter-Modal Hypergraph Attention

M2I2HA：基于模态内和模态间超图注意力的多模态目标检测

Xiaofan Yang, Yubin Liu, Wei Pan, Guoqing Chu, Junming Zhang, Jie Zhao, Zhuoqi Man, Xuanming Cao

机构 * Harbin Institute of Technology（哈尔滨工业大学） 纠错

专题命中 红外-可见光融合 ：multi-modal fusion(abstract)；分类 cs.CV

AI总结 针对多模态目标检测中模态内和模态间信息提取及跨模态对齐的挑战，提出基于超图理论的M2I2HA网络，通过多个模块实现多模态特征的有效处理，在多模态目标检测任务中取得了最优性能。

Comments 43 pages, 13 figures, The theoretical derivation was refined, some data was updated, and experiments were added