FDSG forecasts future entity labels, bounding boxes, and relationships in video scene graphs and outperforms current methods on Action Genome across DSGG, SGA, and its new SGF task.
Prob- abilistic semantic retrieval for surveillance videos with activity graphs,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
FDSG: Forecasting Dynamic Scene Graphs
FDSG forecasts future entity labels, bounding boxes, and relationships in video scene graphs and outperforms current methods on Action Genome across DSGG, SGA, and its new SGF task.