@article{learningstructuredvisualcompositionalrep,
  title = {Learning Structured Visual Compositional Representations for Weakly Supervised Referring Expression Comprehension},
  author = {Lian Xu and Mohammed Bennamoun and Farid Boussaid and Hamid Laga and Yulan Guo and Dan Xu},
  year = {2026},
  eprint = {2607.04638},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2607.04638},
}