Login / Signup
Dual-Scale Alignment-Based Transformer on Linguistic Skeleton Tags for Non-Autoregressive Video Captioning.
Xian Zhong
Yi Zhang
Shuqin Chen
Zhixin Sun
Huantao Zheng
Kui Jiang
Published in:
ICME (2022)
Keyphrases
</>
autoregressive
moving average
non stationary
video sequences
video data
gaussian markov random field
random fields
random field models
autoregressive model
scale space
sar images
spectrum analysis
natural language
image analysis
high frequency
part of speech