AutoCite: Multi-Modal Representation Fusion for Contextual Citation Generation.

Qingqin Wang Yun Xiong Yao Zhang Jiawei Zhang Yangyong Zhu

Published in: WSDM (2021)

Keyphrases

multi modal
multi modality
fusing multiple
audio visual
single modality
cross modal
semantic concepts
higher level
computer vision
image processing
feature space
image annotation
video search
uni modal