O2NA: An Object-Oriented Non-Autoregressive Approach for Controllable Video Captioning.

Fenglin Liu Xuancheng Ren Xian Wu Bang Yang Shen Ge Xu Sun

Published in: CoRR (2021)

Keyphrases

autoregressive
moving average
non stationary
gaussian markov random field
random fields
video data
spectrum analysis
video sequences
random field models
sar images
autoregressive model
text classification
autoregressive moving average
dynamic scenes
co occurrence
hidden markov models
feature space
image sequences