# Robust Emotion Recognition in Context Debiasing

arXiv: https://arxiv.org/abs/2403.05963 · HTML: https://mlsanity.com/paper/2403.05963/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 67 references that are in the map.
- First posted on arXiv 9 Mar 2024.

## Builds on (most cited first, 28 of 28)

- [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)
- [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)
- [Counterfactual VQA: A Cause-Effect Look at Language Bias](https://mlsanity.com/paper/2006.04315/) (2020)
- [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)
- [Discovering Causal Signals in Images](https://mlsanity.com/paper/1605.08179/) (2016)
- [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)
- [Visual Causal Feature Learning](https://mlsanity.com/paper/1412.2309/) (2014)
- [Generalized Video Anomaly Event Detection: Systematic Taxonomy and Comparison of Deep Models](https://mlsanity.com/paper/2302.05087/) (2023)
- [M3ER: Multiplicative Multimodal Emotion Recognition Using Facial, Textual, and Speech Cues](https://mlsanity.com/paper/1911.05659/) (2019)
- [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)
- [AIDE: A Vision-Driven Multi-View, Multi-Modal, Multi-Tasking Dataset for Assistive Driving Perception](https://mlsanity.com/paper/2307.13933/) (2023)
- [STEP: Spatial Temporal Graph Convolutional Networks for Emotion Perception from Gaits](https://mlsanity.com/paper/1910.12906/) (2019)
- [TSA-Net: Tube Self-Attention Network for Action Quality Assessment](https://mlsanity.com/paper/2201.03746/) (2022)
- [Context De-confounded Emotion Recognition](https://mlsanity.com/paper/2303.11921/) (2023)
- [Learning Appearance-motion Normality for Video Anomaly Detection](https://mlsanity.com/paper/2207.13361/) (2022)
- [MISS: A Generative Pretraining and Finetuning Approach for Med-VQA](https://mlsanity.com/paper/2401.05163/) (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)
- [Adversarial Contrastive Distillation with Adaptive Denoising](https://mlsanity.com/paper/2302.08764/) (2023)
- [Sampling to Distill: Knowledge Transfer from Open-World Data](https://mlsanity.com/paper/2307.16601/) (2023)
- [High-Level Context Representation for Emotion Recognition in Images](https://mlsanity.com/paper/2305.03500/) (2023)

## Built on by (most cited first, 24 of 24)

- [Correlation-Decoupled Knowledge Distillation for Multimodal Sentiment Analysis with Incomplete Modalities](https://mlsanity.com/paper/2404.16456/) (2024)
- [Resolving Evidence Sparsity: Agentic Context Engineering for Long-Document Understanding](https://mlsanity.com/paper/2511.22850/) (2025)
- [Knowledge-Aligned Counterfactual-Enhancement Diffusion Perception for Unsupervised Cross-Domain Visual Emotion Recognition](https://mlsanity.com/paper/2505.19694/) (2025)
- [VLLMs Provide Better Context for Emotion Understanding Through Common Sense Reasoning](https://mlsanity.com/paper/2404.07078/) (2024)
- [PediatricsGPT: Large Language Models as Chinese Medical Assistants for Pediatric Applications](https://mlsanity.com/paper/2405.19266/) (2024)
- [Toward Robust Incomplete Multimodal Sentiment Analysis via Hierarchical Representation Learning](https://mlsanity.com/paper/2411.02793/) (2024)
- [Large Vision-Language Models as Emotion Recognizers in Context Awareness](https://mlsanity.com/paper/2407.11300/) (2024)
- [De-confounded Data-free Knowledge Distillation for Handling Distribution Shifts](https://mlsanity.com/paper/2403.19539/) (2024)
- [Efficiency in Focus: LayerNorm as a Catalyst for Fine-tuning Medical Visual Language Pre-trained Models](https://mlsanity.com/paper/2404.16385/) (2024)
- [Towards Context-Aware Emotion Recognition Debiasing from a Causal Demystification Perspective via De-confounded Training](https://mlsanity.com/paper/2407.04963/) (2024)
- [Asynchronous Multimodal Video Sequence Fusion via Learning Modality-Exclusive and -Agnostic Representations](https://mlsanity.com/paper/2407.04955/) (2024)
- [StimuVAR: Spatiotemporal Stimuli-aware Video Affective Reasoning with Multimodal Large Language Models](https://mlsanity.com/paper/2409.00304/) (2024)
- [Improving Multimodal Sentiment Analysis via Modality Optimization and Dynamic Primary Modality Selection](https://mlsanity.com/paper/2511.06328/) (2025)
- [Beyond Spurious Signals: Debiasing Multimodal Large Language Models via Counterfactual Inference and Adaptive Expert Routing](https://mlsanity.com/paper/2509.15361/) (2025)
- [Self-Cooperation Knowledge Distillation for Novel Class Discovery](https://mlsanity.com/paper/2407.01930/) (2024)
- [Disentangling Bias by Modeling Intra- and Inter-modal Causal Attention for Multimodal Sentiment Analysis](https://mlsanity.com/paper/2508.04999/) (2025)
- [Bridging Minds and Machines: Toward an Integration of AI and Cognitive Science](https://mlsanity.com/paper/2508.20674/) (2025)
- [Multi-Scale Heterogeneity-Aware Hypergraph Representation for Histopathology Whole Slide Images](https://mlsanity.com/paper/2404.19334/) (2024)
- [Emotion Knowledge Enhancement for Vision Large Language Models: A Self-Verification Approach for High-Quality Emotion Instruction Data Generation](https://mlsanity.com/paper/2505.18168/) (2025)
- [AGCD-Net: Attention Guided Context Debiasing Network for Emotion Recognition](https://mlsanity.com/paper/2507.09248/) (2025)
- [FSRF: Factorization-guided Semantic Recovery for Incomplete Multimodal Sentiment Analysis](https://mlsanity.com/paper/2510.16086/) (2025)
- [Domain-Agnostic Causal-Aware Audio Transformer for Infant Cry Classification](https://mlsanity.com/paper/2512.16271/) (2025)
- [Faithful Action-unit Causal Reasoning for Counterfactually Faithful Emotion Explanations](https://mlsanity.com/paper/2606.15779/) (2026)
- [A Controlled Study of CLIP-Based Body-Scene Fusion for Emotion Recognition in Context](https://mlsanity.com/paper/2606.22072/) (2026)

## Abstract (arXiv)

Context-aware emotion recognition (CAER) has recently boosted the practical applications of affective computing techniques in unconstrained environments. Mainstream CAER methods invariably extract ensemble representations from diverse contexts and subject-centred characteristics to perceive the target person's emotional state. Despite advancements, the biggest challenge remains due to context bias interference. The harmful bias forces the models to rely on spurious correlations between background contexts and emotion labels in likelihood estimation, causing severe performance bottlenecks and confounding valuable context priors. In this paper, we propose a counterfactual emotion inference (CLEF) framework to address the above issue. Specifically, we first formulate a generalized causal graph to decouple the causal relationships among the variables in CAER. Following the causal graph, CLEF introduces a non-invasive context branch to capture the adverse direct effect caused by the context bias. During the inference, we eliminate the direct context effect from the total causal effect by comparing factual and counterfactual outcomes, resulting in bias mitigation and robust prediction. As a model-agnostic framework, CLEF can be readily integrated into existing methods, bringing consistent performance gains.