A Unified Object-Centric Spatio-Temporal Graph Reasoning Framework for Audio-Visual Question Answering.

@inproceedings{xu-2026-unified, author = {Feifei Xu and Wenjing Zhu and Dongyang Li and Puzhe Li and Luobin Huang and Yu Xie and Zirui Xu}, editor = {Stevan Rudinac and Zi Huang and Marcel Worring and Lucia Vadicamo and Xirong Li and Pascal Mettes and Lizi Liao}, title = {{A Unified Object-Centric Spatio-Temporal Graph Reasoning Framework for Audio-Visual Question Answering}}, booktitle = {{Proceedings of the 2026 International Conference on Multimedia Retrieval, ICMR 2026, Amsterdam, The Netherlands, June 16-19, 2026}}, pages = {1006--1014}, publisher = {ACM}, year = {2026}, url = {https://doi.org/10.1145/3805622.3810845}, doi = {https://doi.org/10.1145/3805622.3810845} }