MACH explicitly models reusable cross-modal agreement and conflict with hierarchical prototype hypergraphs and improves intent recognition on two benchmarks.
Graph mixture of experts with differential cross-attention alignment for multimodal intent recognition,
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.MM 1years
2026 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Modality Agreement- and Conflict-Aware Prototype Hypergraph Learning for Multimodal Intent Understanding
MACH explicitly models reusable cross-modal agreement and conflict with hierarchical prototype hypergraphs and improves intent recognition on two benchmarks.