MVE-QGCAF: Multi-Grained visual evidence construction and question-guided gated cross-attention fusion for medical visual question answering

Yuhai Yu; Lin Lu; Jiana Meng; Jing Liu; Shan Lu; Long Li

doi:10.1007/s44443-026-00936-8

10.1007/s44443-026-00936-8 401 المشاهدات 0 الاقتباسات

الاقتباسات

401

المشاهدات

الملخص غير متوفر لهذا المنشور.

الاستشهاد بهذا المقال (APA)

Yuhai, Y., Lin, L., Jiana, M., Jing, L., Shan, L., Long, L. (2026). MVE-QGCAF: Multi-Grained visual evidence construction and question-guided gated cross-attention fusion for medical visual question answering. Journal of King Saud University - Computer and Information Sciences. https://doi.org/10.1007/s44443-026-00936-8

Zhizhong Xing; Leping Li; Ying Yang; Wei Zhou; Guolan Ma; Shaochun Chen; Lechun · 2026

استشهاد

425

DDM-YOLO: A lightweight oriented detection model for mature daylily fruits in complex environments

Minqiu Kuang; Xuejie Zou; Fangping Xie; Xiaojian Li; Shang Chen; Dawei Liu; Yuxu · 2026

استشهاد

430

Information guided Levy flight for robot search in unknown environments

Weitao Zhao; Zati Hakim Azizul; Xin Lyu; Weijie Kuang · 2026

استشهاد

411

SemCap: Sentiment-aware semantic captioning for multimodal aspect-based sentiment analysis