SliceCSRef: Dual-Level Semantic Alignment for Robust Speech Referring Expression Comprehension.

@inproceedings{huang-2026-slicecsref, author = {Lihong Huang and Sheng-Hua Zhong and Qiao Yan and Zhijiao Xiao and Yan Liu}, editor = {Stevan Rudinac and Zi Huang and Marcel Worring and Lucia Vadicamo and Xirong Li and Pascal Mettes and Lizi Liao}, title = {{SliceCSRef: Dual-Level Semantic Alignment for Robust Speech Referring Expression Comprehension}}, booktitle = {{Proceedings of the 2026 International Conference on Multimedia Retrieval, ICMR 2026, Amsterdam, The Netherlands, June 16-19, 2026}}, pages = {1308--1316}, publisher = {ACM}, year = {2026}, url = {https://doi.org/10.1145/3805622.3810703}, doi = {https://doi.org/10.1145/3805622.3810703} }