B-HFA: Parameter-Efficient Vision-Language Retrieval via Block-shared Adapters and Hierarchical Aggregation.

@inproceedings{xu-2026-bhfa, author = {Rui Xu and Lin Yao and Zhiyang Wu and Xuyun Zhang and Guowei Wu}, editor = {Stevan Rudinac and Zi Huang and Marcel Worring and Lucia Vadicamo and Xirong Li and Pascal Mettes and Lizi Liao}, title = {{B-HFA: Parameter-Efficient Vision-Language Retrieval via Block-shared Adapters and Hierarchical Aggregation}}, booktitle = {{Proceedings of the 2026 International Conference on Multimedia Retrieval, ICMR 2026, Amsterdam, The Netherlands, June 16-19, 2026}}, pages = {242--251}, publisher = {ACM}, year = {2026}, url = {https://doi.org/10.1145/3805622.3810607}, doi = {https://doi.org/10.1145/3805622.3810607} }