@article{simvgasimpleframeworkforvisualgrounding,
  title = {SimVG: A Simple Framework for Visual Grounding with Decoupled Multi-modal Fusion},
  author = {Ming Dai and Lingfeng Yang and Yihao Xu and ZhenHua Feng and Wankou Yang},
  year = {2024},
  eprint = {2409.17531},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2409.17531v2},
}