MIntOOD mixes synthetic out-of-distribution features from multiple known intent classes and learns weighted multimodal fusion with binary, cosine-classifier, and contrastive losses, improving OOD AUROC by 2.5 to 8.4 points and ID accuracy by 0.5 to 1.7 points over baselines on three datasets.
Building multi-turn query interpreters for e-commercial chatbots with sparse-to-dense attentive modeling,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
other 1
citation-polarity summary
fields
cs.MM 1years
2024 1verdicts
CONDITIONAL 1roles
other 1polarities
unclear 1representative citing papers
citing papers explorer
-
Multimodal Classification and Out-of-distribution Detection for Multimodal Intent Understanding
MIntOOD mixes synthetic out-of-distribution features from multiple known intent classes and learns weighted multimodal fusion with binary, cosine-classifier, and contrastive losses, improving OOD AUROC by 2.5 to 8.4 points and ID accuracy by 0.5 to 1.7 points over baselines on three datasets.