Improving Semantic Segmentation through Spatio-Temporal Consistency Learned from Videos.

Ankita Pasad Ariel Gordon Tsung-Yi Lin Anelia Angelova

Published in: CoRR (2020)

Keyphrases

temporal consistency
semantic segmentation
superpixels
conditional random fields
weakly supervised
scene classification
object categories
temporal constraints
object class
object classes
video frames
video sequences
processing speed
bounding box
long range
graph structure
hidden markov models
viewpoint