RoME: Role-aware Mixture-of-Expert Transformer for Text-to-Video Retrieval

Published in arXiv preprint, 2022

Burak Satar, Hongyuan Zhu, Hanwang Zhang, Joo-Hwee Lim

A role-aware mixture-of-experts transformer that separates verbs, objects and context for text-to-video retrieval.

arXiv Code

RoME: Role-aware Mixture-of-Expert Transformer for Text-to-Video Retrieval figure

BibTeX
@article{DBLP:journals/corr/abs-2206-12845,
  author       = {Burak Satar and
                  Hongyuan Zhu and
                  Hanwang Zhang and
                  Joo Hwee Lim},
  title        = {RoME: Role-aware Mixture-of-Expert Transformer for Text-to-Video Retrieval},
  journal      = {CoRR},
  volume       = {abs/2206.12845},
  year         = {2022},
  url          = {https://doi.org/10.48550/arXiv.2206.12845},
  doi          = {10.48550/ARXIV.2206.12845},
  eprinttype   = {arXiv},
  eprint       = {2206.12845},
  timestamp    = {Wed, 15 Oct 2025 07:24:01 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2206-12845.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}