# Causal-EVC: Breaking Emotional Spurious Causality via Spatiotemporal Grounding and Counterfactual Intervention

arXiv: https://arxiv.org/abs/2609.36776 · HTML: https://mlsanity.com/paper/2609.36776/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 32 of its 69 references that are in the map.
- First posted on arXiv 29 Sep 2026.

## Builds on (most cited first, 30 of 32)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [CIDEr: Consensus-based Image Description Evaluation](https://mlsanity.com/paper/1411.5726/) (2014)
- [Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regression](https://mlsanity.com/paper/1902.09630/) (2019)
- [OpenAI GPT-5 System Card](https://mlsanity.com/paper/2601.03267/) (2025)
- [SAM 3: Segment Anything with Concepts](https://mlsanity.com/paper/2511.16719/) (2025)
- [VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding](https://mlsanity.com/paper/2501.13106/) (2025)
- [CLEVRER: CoLlision Events for Video REpresentation and Reasoning](https://mlsanity.com/paper/1910.01442/) (2019)
- [VTimeLLM: Empower LLM to Grasp Video Moments](https://mlsanity.com/paper/2311.18445/) (2023)
- [Momentor: Advancing Video Large Language Model with Fine-Grained Temporal Reasoning](https://mlsanity.com/paper/2402.11435/) (2024)
- [Where Does It Exist: Spatio-Temporal Video Grounding for Multi-Form Sentences](https://mlsanity.com/paper/2001.06891/) (2020)
- [TimeSuite: Improving MLLMs for Long Video Understanding via Grounded Tuning](https://mlsanity.com/paper/2410.19702/) (2024)
- [Reconstruction Network for Video Captioning](https://mlsanity.com/paper/1803.11438/) (2018)
- [Emotion-Cause Pair Extraction: A New Task to Emotion Analysis in Texts](https://mlsanity.com/paper/1906.01267/) (2019)
- [MAFW: A Large-scale, Multi-modal, Compound Affective Database for Dynamic Facial Expression Recognition in the Wild](https://mlsanity.com/paper/2208.00847/) (2022)
- [Semantic Grouping Network for Video Captioning](https://mlsanity.com/paper/2102.00831/) (2021)
- [Multimodal Emotion-Cause Pair Extraction in Conversations](https://mlsanity.com/paper/2110.08020/) (2021)
- [Eliciting In-Context Learning in Vision-Language Models for Videos Through Curated Data Distributional Properties](https://mlsanity.com/paper/2311.17041/) (2023)
- [Graph Mixture of Experts and Memory-augmented Routers for Multivariate Time Series Anomaly Detection](https://mlsanity.com/paper/2412.19108/) (2024)
- [Continual Multimodal Contrastive Learning](https://mlsanity.com/paper/2503.14963/) (2025)
- [CaReBench: A Fine-Grained Benchmark for Video Captioning and Retrieval](https://mlsanity.com/paper/2501.00513/) (2024)
- [Towards Efficient Partially Relevant Video Retrieval with Active Moment Discovering](https://mlsanity.com/paper/2504.10920/) (2025)
- [MME-Emotion: A Holistic Evaluation Benchmark for Emotional Intelligence in Multimodal Large Language Models](https://mlsanity.com/paper/2508.09210/) (2025)
- [Dual-path Collaborative Generation Network for Emotional Video Captioning](https://mlsanity.com/paper/2408.03006/) (2024)
- [HUME: Measuring the Human-Model Performance Gap in Text Embedding Tasks](https://mlsanity.com/paper/2510.10062/) (2025)
- [IF-VidCap: Can Video Caption Models Follow Instructions?](https://mlsanity.com/paper/2510.18726/) (2025)
- [Emotion Prediction Oriented method with Multiple Supervisions for Emotion-Cause Pair Extraction](https://mlsanity.com/paper/2302.12417/) (2023)

## Abstract (arXiv)

Emotional Video Captioning aims to generate factually accurate and emotionally empathetic descriptions. While recent methods have recognized the importance of visual causes to guide emotion perception and caption generation, they fundamentally rely on simple attention matching, which inevitably suffers from {causal redundancy and spurious correlations} in co-occurrence bias (e.g., misclassifying ``sadness'' as ``joy'' on a sunny beach), leading to severe shortcut learning from confusing backgrounds. Furthermore, existing evaluations fail to verify whether models have genuinely mastered causal reasoning or merely exploited background confounders. To address these limitations, we first construct {EVC-CauseGround}, a comprehensive benchmark with dense spatio-temporal causal annotations. Crucially, it introduces a carefully selected {Causal-Faithfulness Subset} to explicitly quantify genuine emotion-cause attribution. Second, we propose {Causal-EVC}, an emotion-grounding captioning framework, which introduces a Motion-guided Causal Spatiotemporal Localization module to precisely decouple causal triggers from background confounders. Besides, we introduce an Interpretable Sparse Emotion Routing module. By synthesizing counterfactual representations and formulating a novel counterfactual contrastive objective, we enforce the model to anchor its emotion predictions strictly on authentic causal triggers instead of confusing background. Extensive experiments show that Causal-EVC not only achieves the best performance on semantic metrics but also exhibits significant advantages in the causal-faithfulness subset, which demonstrates that our model could mine emotional cues from genuine visual causes and mitigate co-occurrence bias for interpretable multimodal emotion understanding.