Universal Captioner: Long-Tail Vision-and-Language Model Training through Content-Style Separation

By Marcella Cornia, Lorenzo Baraldi, Giuseppe Fiameni, Rita Cucchiara. 2021

16 citations recorded by the source corpus.

Subfields: Multimodal Learning, Natural Language Generation

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Multimodal Learning

1. Zhe Gan
2. Lijuan Wang
3. Zicheng Liu
4. Jianfeng Wang
5. Linjie Li
6. Xiaowei Hu
7. Zhengyuan Yang
8. Ce Liu

In Natural Language Generation

1. Rita Cucchiara
2. Lorenzo Baraldi
3. Marcella Cornia
4. Giuseppe Fiameni
5. Matteo Stefanini
6. Zhengyuan Yang
7. Silvia Cascianelli
8. Jiasen Lu

Citations in the corpus

• GIT: A Generative Image-to-text Transformer for Vision and Language (2022, background): “(2021a), UniversalCap: (Cornia et al., 2021) ViTCap: Fang et al.”
• Unified-IO: A Unified Model for Vision, Language, and Multi-Modal Tasks (2022, methodology): “Since U NIFIED -IO is trained on many captioning datasets, it is likely the use of style tags following Cornia et al. (2021) would offer additional improvement by signaling U NIFIED -IO to specifically generate COCO-style captions during inference.”
• From Show to Tell: A Survey on Deep Learning-Based Image Captioning (2021, methodology): “tion to increase generalization and promoting long-tail concepts [97], specializing in particular domains and generating captions with different styles and aims is still”