Unleash the Power of Vision-Language Models by Visual Attention Prompt and Multimodal Interaction

@article{zhang2025unleash,
  title = {Unleash the Power of Vision-Language Models by Visual Attention Prompt and Multimodal Interaction},
  author = {Wenyao Zhang and Le Wu and Zequn Zhang and Tao Yu and Chao Ma and Xin Jin and Xiaokang Yang and Wenjun Zeng},
  year = {2025},
  journal = {IEEE transactions on multimedia},
  doi = {10.1109/TMM.2024.3521785},
  url = {https://doi.org/10.1109/TMM.2024.3521785},
}