# Towards Context-Aware Emotion Recognition Debiasing from a Causal Demystification Perspective via De-confounded Training

arXiv: https://arxiv.org/abs/2407.04963 · HTML: https://mlsanity.com/paper/2407.04963/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 86 references that are in the map.
- First posted on arXiv 6 Jul 2024.

## Builds on (most cited first, 30 of 33)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [SSD: Single Shot MultiBox Detector](https://mlsanity.com/paper/1512.02325/) (2015)
- [Shortcut Learning in Deep Neural Networks](https://mlsanity.com/paper/2004.07780/) (2020)
- [Show, Attend and Tell: Neural Image Caption Generation with Visual Attention](https://mlsanity.com/paper/1502.03044/) (2015)
- [R-FCN: Object Detection via Region-based Fully Convolutional Networks](https://mlsanity.com/paper/1605.06409/) (2016)
- [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)
- [Dawn of the transformer era in speech emotion recognition: closing the valence gap](https://mlsanity.com/paper/2203.07378/) (2022)
- [CausalGAN: Learning Causal Implicit Generative Models with Adversarial Training](https://mlsanity.com/paper/1709.02023/) (2017)
- [Visual Commonsense R-CNN](https://mlsanity.com/paper/2002.12204/) (2020)
- [Context-Aware Emotion Recognition Networks](https://mlsanity.com/paper/1908.05913/) (2019)
- [Two Causal Principles for Improving Visual Dialog](https://mlsanity.com/paper/1911.10496/) (2019)
- [Context Based Emotion Recognition using EMOTIC Dataset](https://mlsanity.com/paper/2003.13401/) (2020)
- [iMiGUE: An Identity-free Video Dataset for Micro-Gesture Understanding and Emotion Analysis](https://mlsanity.com/paper/2107.00285/) (2021)
- [SEWA DB: A Rich Database for Audio-Visual Emotion and Sentiment Research in the Wild](https://mlsanity.com/paper/1901.02839/) (2019)
- [Detecting and Evaluating Medical Hallucinations in Large Vision Language Models](https://mlsanity.com/paper/2406.10185/) (2024)
- [Spatio-Temporal Domain Awareness for Multi-Agent Collaborative Perception](https://mlsanity.com/paper/2307.13929/) (2023)
- [EmotiCon: Context-Aware Multimodal Emotion Recognition using Frege's Principle](https://mlsanity.com/paper/2003.06692/) (2020)
- [Contemplating Visual Emotions: Understanding and Overcoming Dataset Bias](https://mlsanity.com/paper/1808.02212/) (2018)
- [AIDE: A Vision-Driven Multi-View, Multi-Modal, Multi-Tasking Dataset for Assistive Driving Perception](https://mlsanity.com/paper/2307.13933/) (2023)
- [Context De-confounded Emotion Recognition](https://mlsanity.com/paper/2303.11921/) (2023)
- [Counterfactually-Augmented SNLI Training Data Does Not Yield Better Generalization Than Unaugmented Data](https://mlsanity.com/paper/2010.04762/) (2020)
- [Towards Multimodal Sentiment Analysis Debiasing via Bias Purification](https://mlsanity.com/paper/2403.05023/) (2024)
- [De-biasing Distantly Supervised Named Entity Recognition via Causal Intervention](https://mlsanity.com/paper/2106.09233/) (2021)
- [Robust Emotion Recognition in Context Debiasing](https://mlsanity.com/paper/2403.05963/) (2024)
- [CA-SpaceNet: Counterfactual Analysis for 6D Pose Estimation in Space](https://mlsanity.com/paper/2207.07869/) (2022)
- [Text-oriented Modality Reinforcement Network for Multimodal Sentiment Analysis from Unaligned Multimodal Sequences](https://mlsanity.com/paper/2307.13205/) (2023)
- [Causal Intervention for Subject-Deconfounded Facial Action Unit Recognition](https://mlsanity.com/paper/2204.07935/) (2022)

## Built on by (most cited first, 11 of 11)

- [Dolphin-v2: Universal Document Parsing via Scalable Anchor Prompting](https://mlsanity.com/paper/2602.05384/) (2026)
- [Resolving Evidence Sparsity: Agentic Context Engineering for Long-Document Understanding](https://mlsanity.com/paper/2511.22850/) (2025)
- [Toward Robust Incomplete Multimodal Sentiment Analysis via Hierarchical Representation Learning](https://mlsanity.com/paper/2411.02793/) (2024)
- [CausalVAD: De-confounding End-to-End Autonomous Driving via Causal Intervention](https://mlsanity.com/paper/2603.18561/) (2026)
- [Towards Deeper Emotional Reflection: Crafting Affective Image Filters with Generative Priors](https://mlsanity.com/paper/2512.17376/) (2025)
- [UniEmoX: Cross-modal Semantic-Guided Large-Scale Pretraining for Universal Scene Emotion Perception](https://mlsanity.com/paper/2409.18877/) (2024)
- [SatireDecoder: Visual Cascaded Decoupling for Enhancing Satirical Image Comprehension](https://mlsanity.com/paper/2512.00582/) (2025)
- [Disentangling Bias by Modeling Intra- and Inter-modal Causal Attention for Multimodal Sentiment Analysis](https://mlsanity.com/paper/2508.04999/) (2025)
- [Explainable Multimodal Depression Recognition in Clinical Interviews via PHQ-Aligned Symptom Summarization](https://mlsanity.com/paper/2501.16106/) (2025)
- [Weakly Semi-supervised Whole Slide Image Classification by Two-level Cross Consistency Supervision](https://mlsanity.com/paper/2504.12132/) (2025)
- [AGCD-Net: Attention Guided Context Debiasing Network for Emotion Recognition](https://mlsanity.com/paper/2507.09248/) (2025)

## Abstract (arXiv)

Understanding emotions from diverse contexts has received widespread attention in computer vision communities. The core philosophy of Context-Aware Emotion Recognition (CAER) is to provide valuable semantic cues for recognizing the emotions of target persons by leveraging rich contextual information. Current approaches invariably focus on designing sophisticated structures to extract perceptually critical representations from contexts. Nevertheless, a long-neglected dilemma is that a severe context bias in existing datasets results in an unbalanced distribution of emotional states among different contexts, causing biased visual representation learning. From a causal demystification perspective, the harmful bias is identified as a confounder that misleads existing models to learn spurious correlations based on likelihood estimation, limiting the models' performance. To address the issue, we embrace causal inference to disentangle the models from the impact of such bias, and formulate the causalities among variables in the CAER task via a customized causal graph. Subsequently, we present a Contextual Causal Intervention Module (CCIM) to de-confound the confounder, which is built upon backdoor adjustment theory to facilitate seeking approximate causal effects during model training. As a plug-and-play component, CCIM can easily integrate with existing approaches and bring significant improvements. Systematic experiments on three datasets demonstrate the effectiveness of our CCIM.