M-STAR: Multi-view Semantic Topology Alignment with Reasoning from VLMs for Image-Text Retrieval.

@inproceedings{he-2026-mstar, author = {Xuewen He and Yuning Guo and Fumao Xu and Mingyong Li}, editor = {Stevan Rudinac and Zi Huang and Marcel Worring and Lucia Vadicamo and Xirong Li and Pascal Mettes and Lizi Liao}, title = {{M-STAR: Multi-view Semantic Topology Alignment with Reasoning from VLMs for Image-Text Retrieval}}, booktitle = {{Proceedings of the 2026 International Conference on Multimedia Retrieval, ICMR 2026, Amsterdam, The Netherlands, June 16-19, 2026}}, pages = {118--127}, publisher = {ACM}, year = {2026}, url = {https://doi.org/10.1145/3805622.3810824}, doi = {https://doi.org/10.1145/3805622.3810824} }