HCL learns hierarchical multimodal representations via latent variables, structural sparsity, and structure-aware contrastive loss, with identifiability proofs under uncorrelated latents and improved performance on EHR data.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
The Dual-Branch Rebalancing Framework (DBR) mitigates shared-private branch imbalance in multimodal sentiment analysis via Temporal-Structural Factorization, Anchor-Guided Private Routing, and Bidirectional Rebalancing Fusion, outperforming baselines on CMU-MOSI, CMU-MOSEI, and MIntRec.
citing papers explorer
-
Hierarchical Contrastive Learning for Multimodal Data
HCL learns hierarchical multimodal representations via latent variables, structural sparsity, and structure-aware contrastive loss, with identifiability proofs under uncorrelated latents and improved performance on EHR data.
-
Mitigating Shared-Private Branch Imbalance via Dual-Branch Rebalancing for Multimodal Sentiment Analysis
The Dual-Branch Rebalancing Framework (DBR) mitigates shared-private branch imbalance in multimodal sentiment analysis via Temporal-Structural Factorization, Anchor-Guided Private Routing, and Bidirectional Rebalancing Fusion, outperforming baselines on CMU-MOSI, CMU-MOSEI, and MIntRec.