# Debiased Multimodal Understanding for Human Language Sequences

arXiv: https://arxiv.org/abs/2403.05025 · HTML: https://mlsanity.com/paper/2403.05025/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 48 references that are in the map.
- First posted on arXiv 8 Mar 2024.

## Builds on (most cited first, 25 of 25)

- [Gaussian Error Linear Units (GELUs)](https://mlsanity.com/paper/1606.08415/) (2016)
- [Show, Attend and Tell: Neural Image Caption Generation with Visual Attention](https://mlsanity.com/paper/1502.03044/) (2015)
- [Multimodal Transformer for Unaligned Multimodal Language Sequences](https://mlsanity.com/paper/1906.00295/) (2019)
- [Tensor Fusion Network for Multimodal Sentiment Analysis](https://mlsanity.com/paper/1707.07250/) (2017)
- [Unbiased Scene Graph Generation from Biased Training](https://mlsanity.com/paper/2002.11949/) (2020)
- [Deep Facial Expression Recognition: A Survey](https://mlsanity.com/paper/1804.08348/) (2018)
- [Efficient Low-rank Multimodal Fusion with Modality-Specific Factors](https://mlsanity.com/paper/1806.00064/) (2018)
- [MISA: Modality-Invariant and -Specific Representations for Multimodal Sentiment Analysis](https://mlsanity.com/paper/2005.03545/) (2020)
- [MOSI: Multimodal Corpus of Sentiment Intensity and Subjectivity Analysis in Online Opinion Videos](https://mlsanity.com/paper/1606.06259/) (2016)
- [Learning Modality-Specific Representations with Self-Supervised Multi-Task Learning for Multimodal Sentiment Analysis](https://mlsanity.com/paper/2102.04830/) (2021)
- [Learning Factorized Multimodal Representations](https://mlsanity.com/paper/1806.06176/) (2018)
- [Found in Translation: Learning Robust Joint Representations by Cyclic Translations Between Modalities](https://mlsanity.com/paper/1812.07809/) (2018)
- [MultiBench: Multiscale Benchmarks for Multimodal Representation Learning](https://mlsanity.com/paper/2107.07502/) (2021)
- [UR-FUNNY: A Multimodal Language Dataset for Understanding Humor](https://mlsanity.com/paper/1904.06618/) (2019)
- [Improving Multimodal Fusion with Hierarchical Mutual Information Maximization for Multimodal Sentiment Analysis](https://mlsanity.com/paper/2109.00412/) (2021)
- [Causal Attention for Vision-Language Tasks](https://mlsanity.com/paper/2103.03493/) (2021)
- [Words Can Shift: Dynamically Adjusting Word Representations Using Nonverbal Behaviors](https://mlsanity.com/paper/1811.09362/) (2018)
- [Deconfounded Image Captioning: A Causal Retrospect](https://mlsanity.com/paper/2003.03923/) (2020)
- [Generalized Video Anomaly Event Detection: Systematic Taxonomy and Comparison of Deep Models](https://mlsanity.com/paper/2302.05087/) (2023)
- [Causal Reasoning from Meta-reinforcement Learning](https://mlsanity.com/paper/1901.08162/) (2019)
- [Spatio-Temporal Domain Awareness for Multi-Agent Collaborative Perception](https://mlsanity.com/paper/2307.13929/) (2023)
- [CubeMLP: An MLP-based Model for Multimodal Sentiment Analysis and Depression Estimation](https://mlsanity.com/paper/2207.14087/) (2022)
- [Counterfactually-Augmented SNLI Training Data Does Not Yield Better Generalization Than Unaugmented Data](https://mlsanity.com/paper/2010.04762/) (2020)
- [De-biasing Distantly Supervised Named Entity Recognition via Causal Intervention](https://mlsanity.com/paper/2106.09233/) (2021)
- [Causal Intervention for Subject-Deconfounded Facial Action Unit Recognition](https://mlsanity.com/paper/2204.07935/) (2022)

## Built on by (most cited first, 10 of 10)

- [Correlation-Decoupled Knowledge Distillation for Multimodal Sentiment Analysis with Incomplete Modalities](https://mlsanity.com/paper/2404.16456/) (2024)
- [De-confounded Data-free Knowledge Distillation for Handling Distribution Shifts](https://mlsanity.com/paper/2403.19539/) (2024)
- [Towards Context-Aware Emotion Recognition Debiasing from a Causal Demystification Perspective via De-confounded Training](https://mlsanity.com/paper/2407.04963/) (2024)
- [SAIL-Embedding Technical Report: Omni-modal Embedding Foundation Model](https://mlsanity.com/paper/2510.12709/) (2025)
- [Disentangling Bias by Modeling Intra- and Inter-modal Causal Attention for Multimodal Sentiment Analysis](https://mlsanity.com/paper/2508.04999/) (2025)
- [Towards Minimal Causal Representations for Human Multimodal Language Understanding](https://mlsanity.com/paper/2509.21805/) (2025)
- [Multi-Modal Image Fusion via Intervention-Stable Feature Learning](https://mlsanity.com/paper/2603.23272/) (2026)
- [Learning Invariant Modality Representation for Robust Multimodal Learning from a Causal Inference Perspective](https://mlsanity.com/paper/2604.18460/) (2026)
- [Drift-Aware Federated Learning: A Causal Perspective](https://mlsanity.com/paper/2503.09116/) (2025)
- [Reliability-aware Cross-sample Enhancement for Robust Multimodal Sentiment Analysis](https://mlsanity.com/paper/2609.30470/) (2026)

## Abstract (arXiv)

Human multimodal language understanding (MLU) is an indispensable component of expression analysis (e.g., sentiment or humor) from heterogeneous modalities, including visual postures, linguistic contents, and acoustic behaviours. Existing works invariably focus on designing sophisticated structures or fusion strategies to achieve impressive improvements. Unfortunately, they all suffer from the subject variation problem due to data distribution discrepancies among subjects. Concretely, MLU models are easily misled by distinct subjects with different expression customs and characteristics in the training data to learn subject-specific spurious correlations, limiting performance and generalizability across new subjects. Motivated by this observation, we introduce a recapitulative causal graph to formulate the MLU procedure and analyze the confounding effect of subjects. Then, we propose SuCI, a simple yet effective causal intervention module to disentangle the impact of subjects acting as unobserved confounders and achieve model training via true causal effects. As a plug-and-play component, SuCI can be widely applied to most methods that seek unbiased predictions. Comprehensive experiments on several MLU benchmarks clearly show the effectiveness of the proposed module.