ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks ​

← Back to topic

Authors: Jiasen Lu, Dhruv Batra, Devi Parikh, Stefan Lee
Year: 2019
Journal: NeurIPS
DOI: 10.48550/arXiv.1908.02265
Publisher: https://arxiv.org/abs/1908.02265

Keywords: vilbert, vision-language

Abstract ​

We introduce ViLBERT a model for learning task-agnostic joint representations of image content and natural language.

Cite this paper ​

@misc{vilbert2019,
  title  = {ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks},
  author = {Jiasen Lu, Dhruv Batra, Devi Parikh, Stefan Lee},
  year   = {2019},
  journal = {NeurIPS},
  doi    = {10.48550/arXiv.1908.02265},
  url    = {https://doi.org/10.48550/arXiv.1908.02265},
}

Source files ​

• metadata.json
• paper.bib