Decoupling Multimodal Perception and Reasoning for Image Reasoning Segmentation with Large Language Models.

@inproceedings{shen-2026-decoupling, author = {Yiqing Shen and Feng Chen}, editor = {Stevan Rudinac and Zi Huang and Marcel Worring and Lucia Vadicamo and Xirong Li and Pascal Mettes and Lizi Liao}, title = {{Decoupling Multimodal Perception and Reasoning for Image Reasoning Segmentation with Large Language Models}}, booktitle = {{Proceedings of the 2026 International Conference on Multimedia Retrieval, ICMR 2026, Amsterdam, The Netherlands, June 16-19, 2026}}, pages = {977--985}, publisher = {ACM}, year = {2026}, url = {https://doi.org/10.1145/3805622.3810843}, doi = {https://doi.org/10.1145/3805622.3810843} }