SKG-VLA: Scene Knowledge Graph Priors for Structured Scene Semantics and Multimodal Reasoning for Decision Making.

@inproceedings{li-2026-skgvla, author = {Zeyu Li and Lei Li}, editor = {Stevan Rudinac and Zi Huang and Marcel Worring and Lucia Vadicamo and Xirong Li and Pascal Mettes and Lizi Liao}, title = {{SKG-VLA: Scene Knowledge Graph Priors for Structured Scene Semantics and Multimodal Reasoning for Decision Making}}, booktitle = {{Proceedings of the 2026 International Conference on Multimedia Retrieval, ICMR 2026, Amsterdam, The Netherlands, June 16-19, 2026}}, pages = {1045--1054}, publisher = {ACM}, year = {2026}, url = {https://doi.org/10.1145/3805622.3810830}, doi = {https://doi.org/10.1145/3805622.3810830} }