# Multimodal Transformer for Unaligned Multimodal Language Sequences

arXiv: https://arxiv.org/abs/1906.00295 · HTML: https://mlsanity.com/paper/1906.00295/

## Key facts

- Cited by 645 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Jun 2019.

## Built on by (most cited first, 30 of 645)

- [Multimodal Learning with Transformers: A Survey](https://mlsanity.com/paper/2206.06488/) (2022)
- [Are Multimodal Transformers Robust to Missing Modality?](https://mlsanity.com/paper/2204.05454/) (2022)
- [Learning Modality-Specific Representations with Self-Supervised Multi-Task Learning for Multimodal Sentiment Analysis](https://mlsanity.com/paper/2102.04830/) (2021)
- [Trusted Multi-View Classification with Dynamic Evidential Fusion](https://mlsanity.com/paper/2204.11423/) (2022)
- [MultiBench: Multiscale Benchmarks for Multimodal Representation Learning](https://mlsanity.com/paper/2107.07502/) (2021)
- [TransTab: Learning Transferable Tabular Transformers Across Tables](https://mlsanity.com/paper/2205.09328/) (2022)
- [Improving Multimodal Fusion with Hierarchical Mutual Information Maximization for Multimodal Sentiment Analysis](https://mlsanity.com/paper/2109.00412/) (2021)
- [CDTrans: Cross-domain Transformer for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2109.06165/) (2021)
- [Learning to Listen: Modeling Non-Deterministic Dyadic Facial Motion](https://mlsanity.com/paper/2204.08451/) (2022)
- [Foundations and Trends in Multimodal Machine Learning: Principles, Challenges, and Open Questions](https://mlsanity.com/paper/2209.03430/) (2022)
- [Rethinking Architecture Design for Tackling Data Heterogeneity in Federated Learning](https://mlsanity.com/paper/2106.06047/) (2021)
- [MMGCN: Multimodal Fusion via Deep Graph Convolution Network for Emotion Recognition in Conversation](https://mlsanity.com/paper/2107.06779/) (2021)
- [Modeling Dense Multimodal Interactions Between Biological Pathways and Histology for Survival Prediction](https://mlsanity.com/paper/2304.06819/) (2023)
- [Retrieving Multimodal Information for Augmented Generation: A Survey](https://mlsanity.com/paper/2303.10868/) (2023)
- [Mind's Eye: Grounded Language Model Reasoning through Simulation](https://mlsanity.com/paper/2210.05359/) (2022)
- [Quantifying & Modeling Multimodal Interactions: An Information Decomposition Framework](https://mlsanity.com/paper/2302.12247/) (2023)
- [Learning Vision-Guided Quadrupedal Locomotion End-to-End with Cross-Modal Transformers](https://mlsanity.com/paper/2107.03996/) (2021)
- [Decoupled Multimodal Distilling for Emotion Recognition](https://mlsanity.com/paper/2303.13802/) (2023)
- [M3Care: Learning with Missing Modalities in Multimodal Healthcare Data](https://mlsanity.com/paper/2210.17292/) (2022)
- [FuseMoE: Mixture-of-Experts Transformers for Fleximodal Fusion](https://mlsanity.com/paper/2402.03226/) (2024)
- [UniMSE: Towards Unified Multimodal Sentiment Analysis and Emotion Recognition](https://mlsanity.com/paper/2211.11256/) (2022)
- [Identifiability Results for Multimodal Contrastive Learning](https://mlsanity.com/paper/2303.09166/) (2023)
- [Multimodal Information Bottleneck: Learning Minimal Sufficient Unimodal and Multimodal Representations](https://mlsanity.com/paper/2210.17444/) (2022)
- [SimMMDG: A Simple and Effective Framework for Multi-modal Domain Generalization](https://mlsanity.com/paper/2310.19795/) (2023)
- [M2FNet: Multi-modal Fusion Network for Emotion Recognition in Conversation](https://mlsanity.com/paper/2206.02187/) (2022)
- [Visuo-Tactile Transformers for Manipulation](https://mlsanity.com/paper/2210.00121/) (2022)
- [MM-ViT: Multi-Modal Video Transformer for Compressed Video Action Recognition](https://mlsanity.com/paper/2108.09322/) (2021)
- [Towards a Foundation Model for Partial Differential Equations: Multi-Operator Learning and Extrapolation](https://mlsanity.com/paper/2404.12355/) (2024)
- [Bi-Bimodal Modality Fusion for Correlation-Controlled Multimodal Sentiment Analysis](https://mlsanity.com/paper/2107.13669/) (2021)
- [Visual Acoustic Matching](https://mlsanity.com/paper/2202.06875/) (2022)

## Abstract (arXiv)

Human language is often multimodal, which comprehends a mixture of natural language, facial gestures, and acoustic behaviors. However, two major challenges in modeling such multimodal human language time-series data exist: 1) inherent data non-alignment due to variable sampling rates for the sequences from each modality; and 2) long-range dependencies between elements across modalities. In this paper, we introduce the Multimodal Transformer (MulT) to generically address the above issues in an end-to-end manner without explicitly aligning the data. At the heart of our model is the directional pairwise crossmodal attention, which attends to interactions between multimodal sequences across distinct time steps and latently adapt streams from one modality to another. Comprehensive experiments on both aligned and non-aligned multimodal time-series show that our model outperforms state-of-the-art methods by a large margin. In addition, empirical analysis suggests that correlated crossmodal signals are able to be captured by the proposed crossmodal attention mechanism in MulT.