FReMuRe improves recall of long-tail relationships in video scene graphs via relation-specific branches, frequency-aware predicate embeddings, and new Bayesian/GMM classification heads, with reported gains on the Action Genome dataset.
By employing a frequency-guided dual-branch network and specialized classification heads, FReMuRe effectively decouples the learning of common and rare predicates
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Frequency-guided Multi-level Reasoning for Scene Graph Generation in Video
FReMuRe improves recall of long-tail relationships in video scene graphs via relation-specific branches, frequency-aware predicate embeddings, and new Bayesian/GMM classification heads, with reported gains on the Action Genome dataset.