@article{d3netaspeakerlistenerarchitecturefor,
  title = {D3Net: A Unified Speaker-Listener Architecture for 3D Dense Captioning and Visual Grounding},
  author = {Dave Zhenyu Chen and Qirui Wu and Matthias Nießner and Angel X. Chang},
  year = {2021},
  eprint = {2112.01551},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2112.01551v2},
}