A Multi-scale Multi-modal Multi-dimension Joint Transformer for Two-Stream Action Classification.

Lin Wang Ammar Hawbani Yan Xiong

Published in: PRICAI (3) (2023)

Keyphrases

multi modal
action classification
multiscale
action recognition
bag of words
high dimensional
human actions
data streams
static images
global features
image representation
image annotation
semantic concepts
image processing
spatio temporal
uni modal
space time
human motion
graph cuts
keywords
multimedia