UniFormerV2: Spatiotemporal Learning by Arming Image ViTs with Video UniFormer.

Kunchang Li Yali Wang Yinan He Yizhuo Li Yi Wang Limin Wang Yu Qiao

Published in: CoRR (2022)

Keyphrases

image data
learning process
image features
multiscale
image segmentation
image analysis
image content
image pixels
reinforcement learning
input image
image classification
space time
static images
video analysis
learning algorithm
test images
video streams
video images
image matching
single image
low level
high resolution
visual information
video data
image collections
image frames
image retrieval
moving objects