mayug/VDT-Adapter
This repository contains the code and datasets for our ICCV-W paper 'Enhancing CLIP with GPT-4: Harnessing Visual Descriptions as Prompts'
ShellMIT
Stargazers
- EricArazo
- eternaldolphin
- fly51flyPRIS
- HazelSu
- Issac-WestcottWorld
- jianandeng023
- lyuchenyangDublin City University
- MartinserNankai University
- mayug@ml-labs
- mehdidcJuelich Supercomputing Center (JSC), Forschungszentrum Jülich GmbH, LAION
- michalwolsNew York
- MorningStarOvOIIE, CAS
- NemaVatsalaIISER Bhopal
- oindrilasaha
- PaulAlbert31Insight Center for Data Analytics
- QiushiYangCity University of Hong Kong
- rongtongxueyaBeijing Normal University
- shuguang99Harbin Institute of Technology
- smn2010
- XIRZCNull
- xuntianci
- YangShiJun-81
- YiranHuangIrene
- yticad
- zwyang6Fudan University