@article{olvitmultimodalstatetrackingvia,
  title = {OLViT: Multi-Modal State Tracking via Attention-Based Embeddings for Video-Grounded Dialog},
  author = {Adnen Abdessaied and Manuel von Hochmeister and Andreas Bulling},
  year = {2024},
  eprint = {2402.13146},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2402.13146v1},
}