VC-GPT: Visual Conditioned GPT for End-to-End Generative Vision-and-Language Pre-training
By Ziyang Luo, Yadong Xi, Rongsheng Zhang, Jing Ma. 2022
22 citations recorded by the source corpus.
Subfields: Large Language Models, Multimodal Learning
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Large Language Models
- Andrew Zisserman
- Oriol Vinyals
- Antoine Miech
- Jean-Baptiste Alayrac
- Aida Nematzadeh
- Jason Aaron Edward Weston
- Jianfeng Gao
- Quoc V. Le
In Multimodal Learning
- Andrew Zisserman
- Jean-Baptiste Alayrac
- Antoine Miech
- Jeff Donahue
- Oriol Vinyals
- Aida Nematzadeh
- Karen Simonyan
- Cordelia Schmid
Citations in the corpus
- Flamingo: a Visual Language Model for Few-Shot Learning (2022, methodology): “One recent line of work [26, 68, 78, 114, 136, 144] proposes to freeze the pretrained LM weights to prevent catastrophic forgetting [71].”
- Zero-Shot Video Question Answering via Frozen Bidirectional Language Models (2022, unknown): “VisualGPT [13] and VC-GPT [71] showed the benefit of initializing the weights of an image captioning model with a pretrained autoregressive language-only model.”
- GLAZE: Protecting Artists from Style Mimicry by Text-to-Image Models (2023, methodology): “First, we take art pieces from the victim artist V and generate a text caption for each piece using an image captioning model [51].”