Support-Set Based Multi-Modal Representation Enhancement for Video Captioning.

Xiaoya Chen Jingkuan Song Pengpeng Zeng Lianli Gao Heng Tao Shen

Published in: ICME (2022)

Keyphrases

multi modal
video search
multi modality
video sequences
image enhancement
video data
image representation
video streams
audio visual
semantic concepts
fusing multiple
feature selection
multiple modalities
image classification
mutual information
multimedia
image processing