TableVLM: Multi-modal Pre-training for Table Structure Recognition.

Leiyuan Chen Chengsong Huang Xiaoqing Zheng Jinshu Lin Xuanjing Huang

Published in: ACL (1) (2023)

Keyphrases

multi modal
object recognition
audio visual
multi modality
semantic concepts
machine learning
feature extraction
image annotation
cross modal
similarity measure
high dimensional
video search