MOSAIC learns overlap-aware shared-specific representations, fits a first-stage predictor on overlapping data, and calibrates the gap using target-pattern samples, with non-asymptotic error bounds decomposing overlap size, calibration gap, and representation error.
Efficient Low-rank Multimodal Fusion with Modality-Specific Factors
9 Pith papers cite this work. Polarity classification is still indexing.
9
Pith papers citing it
abstract
Multimodal research is an emerging field of artificial intelligence, and one of the main research problems in this field is multimodal fusion. The fusion of multimodal data is the process of integrating multiple unimodal representations into one compact multimodal representation. Previous research in this field has exploited the expressiveness of tensors for multimodal representation. However, these methods often suffer from exponential increase in dimensions and in computational complexity introduced by transformation of input into tensor. In this paper, we propose the Low-rank Multimodal Fusion method, which performs multimodal fusion using low-rank tensors to improve efficiency. We evaluate our model on three different tasks: multimodal sentiment analysis, speaker trait analysis, and emotion recognition. Our model achieves competitive results on all these tasks while drastically reducing computational complexity. Additional experiments also show that our model can perform robustly for a wide range of low-rank settings, and is indeed much more efficient in both training and inference compared to other methods that utilize tensor representations.
citation-role summary
baseline 1
method 1
citation-polarity summary
representative citing papers
Gated Multi-modal Fusion reaches 0.82 macro F1 on HARMES, beating the concatenation baseline of 0.76 by 6 points under leave-one-participant-out evaluation.
MMCI uses multi-relational graph modeling and attention-based disentanglement of causal versus shortcut features, combined with backdoor adjustment, to reduce bias and improve generalization in multimodal sentiment analysis.
A multimodal survival model using attention-based histology features, RNA-seq encoders, and low-rank bilinear fusion shows improved performance over concatenation baselines on the CHIMERA dataset for HR-NMIBC.
A multi-modal extension of multi-expert architectures uses confidence-guided fusion from modality-specific networks to handle long-tailed class imbalance across heterogeneous inputs.
A multimodal generative model replaces Gaussians with t-distributions and uses gamma-power divergence to improve semi-supervised classification performance on imbalanced partially labeled data.
Group Cognition Learning uses governed two-stage agents after separate modality encoding to mitigate dominance and spurious coupling, reporting state-of-the-art results on CMU-MOSI, CMU-MOSEI, and MIntRec for regression and classification.
Introduces CP and SL to balance modalities and stabilize training in MSA, reporting SOTA results on CMU-MOSI with component ablations.
A holistic survey of affective computing for intelligent agents covering emotion understanding via multimodal data, affective cognition, emotional expression synthesis, key challenges, and future directions emphasizing generative technologies.
citing papers explorer
-
Attention-Based Multimodal Survival Prediction with Cross-Modal Bilinear Fusion
A multimodal survival model using attention-based histology features, RNA-seq encoders, and low-rank bilinear fusion shows improved performance over concatenation baselines on the CHIMERA dataset for HR-NMIBC.