MCSP improves unsupervised multimodal intent discovery by using MLLM-generated semantic concepts as anchors and propagating them over a concept-weighted graph before contrastively refining representations.
InProceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, Yaser Al-Onaizan, Mohit Bansal, and Yun-Nung Chen (Eds.)
1 Pith paper cite this work, alongside 6 external citations. Polarity classification is still indexing.
1
Pith paper citing it
6
external citations · OpenAlex
fields
cs.MM 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Unsupervised Multimodal Intent Discovery via MLLM-Guided Concept Generation and Semantic Propagation
MCSP improves unsupervised multimodal intent discovery by using MLLM-generated semantic concepts as anchors and propagating them over a concept-weighted graph before contrastively refining representations.