# MECD: Unlocking Multi-Event Causal Discovery in Video Reasoning

arXiv: https://arxiv.org/abs/2409.17647 · HTML: https://mlsanity.com/paper/2409.17647/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal reasoning, one of 17 directions in LLM reasoning.
- Builds on 47 of its 69 references that are in the map.
- First posted on arXiv 26 Sep 2024.

## Placed in

- LLM reasoning / [Multimodal reasoning](https://mlsanity.com/lr/multimodal-reasoning/)

## Builds on (most cited first, 30 of 47)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding](https://mlsanity.com/paper/2306.02858/) (2023)
- [Video-LLaVA: Learning United Visual Representation by Alignment Before Projection](https://mlsanity.com/paper/2311.10122/) (2023)
- [MVBench: A Comprehensive Multi-modal Video Understanding Benchmark](https://mlsanity.com/paper/2311.17005/) (2023)
- [Dense-Captioning Events in Videos](https://mlsanity.com/paper/1705.00754/) (2017)
- [VideoBERT: A Joint Model for Video and Language Representation Learning](https://mlsanity.com/paper/1904.01766/) (2019)
- [ActivityNet-QA: A Dataset for Understanding Complex Web Videos via Question Answering](https://mlsanity.com/paper/1906.02467/) (2019)
- [CLEVRER: CoLlision Events for Video REpresentation and Reasoning](https://mlsanity.com/paper/1910.01442/) (2019)
- [Unsupervised Feature Extraction by Time-Contrastive Learning and Nonlinear ICA](https://mlsanity.com/paper/1605.06336/) (2016)
- [A Comprehensive Survey of Hallucination Mitigation Techniques in Large Language Models](https://mlsanity.com/paper/2401.01313/) (2024)
- [Self-Chained Image-Language Model for Video Localization and Question Answering](https://mlsanity.com/paper/2305.06988/) (2023)
- [DYNOTEARS: Structure Learning from Time-Series Data](https://mlsanity.com/paper/2002.00498/) (2020)
- [Navigate through Enigmatic Labyrinth A Survey of Chain of Thought Reasoning: Advances, Frontiers and Future](https://mlsanity.com/paper/2309.15402/) (2023)
- [Large Language Models Are Latent Variable Models: Explaining and Finding Good Demonstrations for In-Context Learning](https://mlsanity.com/paper/2301.11916/) (2023)
- [CATER: A diagnostic dataset for Compositional Actions and TEmporal Reasoning](https://mlsanity.com/paper/1910.04744/) (2019)
- [End-to-End Dense Video Captioning with Parallel Decoding](https://mlsanity.com/paper/2108.07781/) (2021)
- [Few-shot training LLMs for project-specific code-summarization](https://mlsanity.com/paper/2207.04237/) (2022)
- [MiniGPT4-Video: Advancing Multimodal LLMs for Video Understanding with Interleaved Visual-Textual Tokens](https://mlsanity.com/paper/2404.03413/) (2024)
- [Causal Attention for Vision-Language Tasks](https://mlsanity.com/paper/2103.03493/) (2021)
- [Large Language Models are Few-shot Testers: Exploring LLM-based General Bug Reproduction](https://mlsanity.com/paper/2209.11515/) (2022)
- [Object Relational Graph with Teacher-Recommended Learning for Video Captioning](https://mlsanity.com/paper/2002.11566/) (2020)
- [Task Contamination: Language Models May Not Be Few-Shot Anymore](https://mlsanity.com/paper/2312.16337/) (2023)
- [High-recall causal discovery for autocorrelated time series with latent confounders](https://mlsanity.com/paper/2007.01884/) (2020)
- [MART: Memory-Augmented Recurrent Transformer for Coherent Video Paragraph Captioning](https://mlsanity.com/paper/2005.05402/) (2020)
- [Causal Discovery in Physical Systems from Videos](https://mlsanity.com/paper/2007.00631/) (2020)
- [Deconfounded Image Captioning: A Causal Retrospect](https://mlsanity.com/paper/2003.03923/) (2020)

## Built on by (most cited first, 23 of 23)

- [VideoRFT: Incentivizing Video Reasoning Capability in MLLMs via Reinforced Fine-Tuning](https://mlsanity.com/paper/2505.12434/) (2025)
- [TRACE: Temporal Grounding Video LLM via Causal Event Modeling](https://mlsanity.com/paper/2410.05643/) (2024)
- [TEMPURA: Temporal Event Masked Prediction and Understanding for Reasoning in Action](https://mlsanity.com/paper/2505.01583/) (2025)
- [Commonsense Video Question Answering through Video-Grounded Entailment Tree Reasoning](https://mlsanity.com/paper/2501.05069/) (2025)
- [Video-LMM Post-Training: A Deep Dive into Video Reasoning with Large Multimodal Models](https://mlsanity.com/paper/2510.05034/) (2025)
- [ADC-GS: Anchor-Driven Deformable and Compressed Gaussian Splatting for Dynamic Scene Reconstruction](https://mlsanity.com/paper/2505.08196/) (2025)
- [Fair Deepfake Detectors Can Generalize](https://mlsanity.com/paper/2507.02645/) (2025)
- [MECD+: Unlocking Event-Level Causal Graph Discovery for Video Reasoning](https://mlsanity.com/paper/2501.07227/) (2025)
- [CSTA: Spatial-Temporal Causal Adaptive Learning for Exemplar-Free Video Class-Incremental Learning](https://mlsanity.com/paper/2501.07236/) (2025)
- [CogStream: Context-guided Streaming Video Question Answering](https://mlsanity.com/paper/2506.10516/) (2025)
- [Looking Beyond Visible Cues: Implicit Video Question Answering via Dual-Clue Reasoning](https://mlsanity.com/paper/2506.07811/) (2025)
- [What Happens When: Learning Temporal Orders of Events in Videos](https://mlsanity.com/paper/2512.08979/) (2025)
- [VidLaDA: Bidirectional Diffusion Large Language Models for Efficient Video Understanding](https://mlsanity.com/paper/2601.17868/) (2026)
- [ChainReaction: Causal Chain-Guided Reasoning for Modular and Explainable Causal-Why Video Question Answering](https://mlsanity.com/paper/2508.21010/) (2025)
- [Mitigating Object Hallucinations in LVLMs via Attention Imbalance Rectification](https://mlsanity.com/paper/2603.24058/) (2026)
- [ViMU: Benchmarking Video Metaphorical Understanding](https://mlsanity.com/paper/2605.14607/) (2026)
- [SVI-Bench: A Dynamic Microworld for Strategic Video Intelligence](https://mlsanity.com/paper/2605.31529/) (2026)
- [Contrastive Representation Distillation via Multi-Scale Feature Decoupling](https://mlsanity.com/paper/2502.05835/) (2025)
- [Event-Causal RAG: A Retrieval-Augmented Generation Framework for Long Video Reasoning in Complex Scenarios](https://mlsanity.com/paper/2605.06185/) (2026)
- [GRACE: Boosting Video MLLMs with Grounded Action-Centric Evidence for Viewer Sentiment Prediction](https://mlsanity.com/paper/2606.16198/) (2026)
- [Learning to Deny: Action Denial in Multimodal Large Language Models](https://mlsanity.com/paper/2606.31187/) (2026)
- [Action- and Language-Conditioned Video Assessment for Embodied Control](https://mlsanity.com/paper/2608.08273/) (2026)
- [Counterfactual Sensitivity Is Not Repairability: Auditing Replay Probes for Video Evidence](https://mlsanity.com/paper/2608.15685/) (2026)

## Abstract (arXiv)

Video causal reasoning aims to achieve a high-level understanding of video content from a causal perspective. However, current video reasoning tasks are limited in scope, primarily executed in a question-answering paradigm and focusing on short videos containing only a single event and simple causal relationships, lacking comprehensive and structured causality analysis for videos with multiple events. To fill this gap, we introduce a new task and dataset, Multi-Event Causal Discovery (MECD). It aims to uncover the causal relationships between events distributed chronologically across long videos. Given visual segments and textual descriptions of events, MECD requires identifying the causal associations between these events to derive a comprehensive, structured event-level video causal diagram explaining why and how the final result event occurred. To address MECD, we devise a novel framework inspired by the Granger Causality method, using an efficient mask-based event prediction model to perform an Event Granger Test, which estimates causality by comparing the predicted result event when premise events are masked versus unmasked. Furthermore, we integrate causal inference techniques such as front-door adjustment and counterfactual inference to address challenges in MECD like causality confounding and illusory causality. Experiments validate the effectiveness of our framework in providing causal relationships in multi-event videos, outperforming GPT-4o and VideoLLaVA by 5.7% and 4.1%, respectively.