The paper introduces MMHCL, a setting where modalities train on heterogeneous category sets, and CSCF, a model using semantic alignment, uncertainty-based dominance selection, and class-similarity fusion to recognize the complete class space.
Deep incomplete multi-view network semi-supervised multi-label learning with unbiased loss
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
-
Class Similarity-Based Multimodal Classification under Heterogeneous Category Sets
The paper introduces MMHCL, a setting where modalities train on heterogeneous category sets, and CSCF, a model using semantic alignment, uncertainty-based dominance selection, and class-similarity fusion to recognize the complete class space.