Login / Signup
ChatGPT Asks, BLIP-2 Answers: Automatic Questioning Towards Enriched Visual Descriptions.
Deyao Zhu
Jun Chen
Kilichbek Haydarov
Xiaoqian Shen
Wenxuan Zhang
Mohamed Elhoseiny
Published in:
Trans. Mach. Learn. Res. (2024)
Keyphrases
</>
high level
low level
visual features
visual information
computer assisted
visual data
real time
web pages
object recognition
vision system
data driven
visual perception
answer questions