ALVG: Training High-Quality Multi-modal Fusion Modules for Visual Grounding with Attention Loss.

@inproceedings{yang-2025-alvg, author = {Sicheng Yang and Rongwei Yu}, editor = {Zhongfei Zhang and Elisa Ricci and Yan Yan and Liqiang Nie and Vincent Oria and Lamberto Ballan}, title = {{ALVG: Training High-Quality Multi-modal Fusion Modules for Visual Grounding with Attention Loss}}, booktitle = {{Proceedings of the 2025 International Conference on Multimedia Retrieval, ICMR 2025, Chicago, IL, USA, 30 June 2025 - 3 July 2025}}, pages = {1700--1709}, publisher = {ACM}, year = {2025}, url = {https://doi.org/10.1145/3731715.3733274}, doi = {https://doi.org/10.1145/3731715.3733274} }