Sign in
Expanding Scene Graph Boundaries: Fully Open-vocabulary Scene Graph Generation via Visual-Concept Alignment and Retention.
Zuyao Chen
Jinlin Wu
Zhen Lei
Zhaoxiang Zhang
Changwen Chen
Published in:
CoRR (2023)
Keyphrases
</>
video sequences
input image
computer vision
keywords
probabilistic model
spatial relations
visual concepts
inter related