SAM3-LiteText: An Anatomical Study of the SAM3 Text Encoder for Efficient Vision-Language Segmentation.

@inproceedings{zeng-2026-sam3litetext, author = {Chengxi Zeng and Yuxuan Jiang and Ge Gao and Shuai Wang and Duolikun Danier and Bin Zhu and Stevan Rudinac and David Bull and Fan Zhang}, editor = {Stevan Rudinac and Zi Huang and Marcel Worring and Lucia Vadicamo and Xirong Li and Pascal Mettes and Lizi Liao}, title = {{SAM3-LiteText: An Anatomical Study of the SAM3 Text Encoder for Efficient Vision-Language Segmentation}}, booktitle = {{Proceedings of the 2026 International Conference on Multimedia Retrieval, ICMR 2026, Amsterdam, The Netherlands, June 16-19, 2026}}, pages = {1147--1156}, publisher = {ACM}, year = {2026}, url = {https://doi.org/10.1145/3805622.3810586}, doi = {https://doi.org/10.1145/3805622.3810586} }