Exploiting Long-Term Dependencies for Generating Dynamic Scene Graphs.

Shengyu Feng Subarna Tripathi Hesham Mostafa Marcel Nassar Somdeb Majumdar

Published in: CoRR (2021)

Keyphrases

dynamic scenes
long term
multi view
space time
video camera
video sequences
background subtraction
frame rate
temporally coherent
static scenes
moving objects
multiple views
temporal coherence
image frames
motion segmentation
camera setups
generative model
semi supervised
active learning