Multi-modal Dependency Tree for Video Captioning.

Wentian Zhao Xinxiao Wu Jiebo Luo

Published in: NeurIPS (2021)

Keyphrases

multi modal
dependency tree
semantic concepts
video search
relation extraction
dependency parsing

video data
multi modality
video sequences
video content
audio visual
multiple modalities

multimedia
video frames
syntactic structures
information retrieval
key frames

sentiment classification
automatic extraction
question answering
keywords
feature extraction