TY - GEN
T1 - Retrieval from Dynamic Phrases
T2 - 2025 International Joint Conference on Neural Networks, IJCNN 2025
AU - Chen, Haoquan
AU - Yan, Bin
AU - Shen, Hongyu
AU - Pei, Mingtao
N1 - Publisher Copyright:
© 2025 IEEE.
PY - 2025
Y1 - 2025
N2 - Most retrieval-based report generation methods rely on sentence-level templates, which often introduce ambiguities due to similar semantics across different sentences. To overcome this, we propose a phrase-level framework, comprising automatic phrase template extraction and report generation based on retrieval. In the first stage, we introduce a phrase scoring mechanism to evaluate the semantics and importance of phrases, enabling efficient template extraction. In the second stage, we retrieve relevant templates and fuse their features with visual features from the radiograph through a Retrieval-Aggregation strategy. The dynamic update of the template bank during training improves template representations. Experiments on IU X-Ray and MIMIC-CXR datasets demonstrate the effectiveness of our method in generating accurate radiology reports.
AB - Most retrieval-based report generation methods rely on sentence-level templates, which often introduce ambiguities due to similar semantics across different sentences. To overcome this, we propose a phrase-level framework, comprising automatic phrase template extraction and report generation based on retrieval. In the first stage, we introduce a phrase scoring mechanism to evaluate the semantics and importance of phrases, enabling efficient template extraction. In the second stage, we retrieve relevant templates and fuse their features with visual features from the radiograph through a Retrieval-Aggregation strategy. The dynamic update of the template bank during training improves template representations. Experiments on IU X-Ray and MIMIC-CXR datasets demonstrate the effectiveness of our method in generating accurate radiology reports.
KW - Dynamic Bank
KW - Phrase Templates
KW - Radiograph Report Generation
KW - Vision-Language Retrieval
UR - https://www.scopus.com/pages/publications/105023975944
U2 - 10.1109/IJCNN64981.2025.11228627
DO - 10.1109/IJCNN64981.2025.11228627
M3 - Conference contribution
AN - SCOPUS:105023975944
T3 - Proceedings of the International Joint Conference on Neural Networks
BT - International Joint Conference on Neural Networks, IJCNN 2025 - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 30 June 2025 through 5 July 2025
ER -