A two-stage framework that factorizes multi-view representations into view-consistent and view-specific parts, using masked reconstruction, semantic contrast, and a graph disentangling loss, outperforms ten baselines on incomplete multi-view multi-label benchmarks.
Clough, Henning M ¨uller, and Thomas Deselaers
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
dataset 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
dataset 1polarities
use dataset 1representative citing papers
citing papers explorer
-
Multi-View Factorizing and Disentangling: A Novel Framework for Incomplete Multi-View Multi-Label Classification
A two-stage framework that factorizes multi-view representations into view-consistent and view-specific parts, using masked reconstruction, semantic contrast, and a graph disentangling loss, outperforms ten baselines on incomplete multi-view multi-label benchmarks.