Login / Signup
Structure-Aware Procedural Text Generation From an Image Sequence.
Taichi Nishimura
Atsushi Hashimoto
Yoshitaka Ushiku
Hirotaka Kameko
Yoko Yamakata
Shinsuke Mori
Published in:
IEEE Access (2021)
Keyphrases
</>
text generation
image sequences
natural language generation
video sequences
data sets
three dimensional
neural network
spatio temporal
structure from motion
depth map
domain independent
structural information
motion segmentation