V2P: Vision-to-Prompt based Multi-Modal Product Summary Generation.

Xuemeng Song Liqiang Jing Dengtian Lin Zhongzhou Zhao Haiqing Chen Liqiang Nie

Published in: SIGIR (2022)

Keyphrases

multi modal
summary generation
computer vision
multi modality
high dimensional
audio visual
cross modal
video search
feature selection
image processing
feature space
medical images