# Video-EM: Event-Centric Episodic Memory for Long-Form Video Understanding

arXiv: https://arxiv.org/abs/2508.09486 · HTML: https://mlsanity.com/paper/2508.09486/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 41 of its 57 references that are in the map.
- First posted on arXiv 13 Aug 2025.

## Builds on (most cited first, 30 of 41)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection](https://mlsanity.com/paper/2303.05499/) (2023)
- [LLaVA-OneVision: Easy Visual Task Transfer](https://mlsanity.com/paper/2408.03326/) (2024)
- [Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding](https://mlsanity.com/paper/2306.02858/) (2023)
- [Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis](https://mlsanity.com/paper/2405.21075/) (2024)
- [EgoSchema: A Diagnostic Benchmark for Very Long-form Video Language Understanding](https://mlsanity.com/paper/2308.09126/) (2023)
- [LLaMA-VID: An Image is Worth 2 Tokens in Large Language Models](https://mlsanity.com/paper/2311.17043/) (2023)
- [MovieChat: From Dense Token to Sparse Memory for Long Video Understanding](https://mlsanity.com/paper/2307.16449/) (2023)
- [Long Context Transfer from Language to Vision](https://mlsanity.com/paper/2406.16852/) (2024)
- [LVBench: An Extreme Long Video Understanding Benchmark](https://mlsanity.com/paper/2406.08035/) (2024)
- [VideoAgent: Long-form Video Understanding with Large Language Model as Agent](https://mlsanity.com/paper/2403.10517/) (2024)
- [LongVILA: Scaling Long-Context Visual Language Models for Long Videos](https://mlsanity.com/paper/2408.10188/) (2024)
- [X-CLIP: End-to-End Multi-grained Contrastive Learning for Video-Text Retrieval](https://mlsanity.com/paper/2207.07285/) (2022)
- [VideoTree: Adaptive Tree-based Video Representation for LLM Reasoning on Long Videos](https://mlsanity.com/paper/2405.19209/) (2024)
- [VideoAgent: A Memory-augmented Multimodal Agent for Video Understanding](https://mlsanity.com/paper/2403.11481/) (2024)
- [A Simple LLM Framework for Long-Range Video Question-Answering](https://mlsanity.com/paper/2312.17235/) (2023)
- [TransNet V2: An effective deep network architecture for fast shot transition detection](https://mlsanity.com/paper/2008.04838/) (2020)
- [Streaming Long Video Understanding with Large Language Models](https://mlsanity.com/paper/2405.16009/) (2024)
- [Adaptive Keyframe Sampling for Long Video Understanding](https://mlsanity.com/paper/2502.21271/) (2025)
- [Video-of-Thought: Step-by-Step Video Reasoning from Perception to Cognition](https://mlsanity.com/paper/2501.03230/) (2024)
- [LongVLM: Efficient Long Video Understanding via Large Language Models](https://mlsanity.com/paper/2404.03384/) (2024)
- [Towards Long-Form Video Understanding](https://mlsanity.com/paper/2106.11310/) (2021)
- [Video-RAG: Visually-aligned Retrieval-Augmented Long Video Comprehension](https://mlsanity.com/paper/2411.13093/) (2024)
- [HourVideo: 1-Hour Video-Language Understanding](https://mlsanity.com/paper/2411.04998/) (2024)
- [TimeSuite: Improving MLLMs for Long Video Understanding via Grounded Tuning](https://mlsanity.com/paper/2410.19702/) (2024)
- [VLM: Task-agnostic Video-Language Model Pre-training for Video Understanding](https://mlsanity.com/paper/2105.09996/) (2021)

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

- [VideoMem: Enhancing Ultra-Long Video Understanding via Adaptive Memory Management](https://mlsanity.com/paper/2512.04540/) (2025)
- [OASIS: On-Demand Hierarchical Event Memory for Streaming Video Reasoning](https://mlsanity.com/paper/2604.17052/) (2026)
- [Event-VStream: Event-Driven Real-Time Understanding for Long Video Streams](https://mlsanity.com/paper/2601.15655/) (2026)
- [Keep It in Mind: User Centric Continual Spatial Intelligence Reasoning in Egocentric Video Streams](https://mlsanity.com/paper/2606.15200/) (2026)
- [Enhancing Partially Relevant Video Retrieval with Robust Alignment Learning](https://mlsanity.com/paper/2509.01383/) (2025)
- [FedCVU: Federated Learning for Cross-View Video Understanding](https://mlsanity.com/paper/2603.21647/) (2026)
- [StoryTeller: Training-Free Narrative Grounding for Long-Form Audio Description](https://mlsanity.com/paper/2607.11798/) (2026)
- [LAVE: Latent Visual Evidence-Enhanced Planning for Video Tool-use Agents](https://mlsanity.com/paper/2608.07585/) (2026)
- [From Intent to Evidence: Policy-Steered Multi-Strategy Retrieval for Long-Video Agents](https://mlsanity.com/paper/2608.31005/) (2026)
- [VideoLoop: Looped Working Memory Against Semantic Thrashing in Long-Form Video Agents](https://mlsanity.com/paper/2609.38119/) (2026)

## Abstract (arXiv)

Video Large Language Models (Video-LLMs) have shown strong video understanding, yet their application to long-form videos remains constrained by limited context windows. A common workaround is to compress long videos into a handful of representative frames via retrieval or summarization. However, most existing pipelines score frames in isolation, implicitly assuming that frame-level saliency is sufficient for downstream reasoning. This often yields redundant selections, fragmented temporal evidence, and weakened narrative grounding for long-form video question answering. We present Video-EM, a training-free, event-centric episodic memory framework that reframes long-form VideoQA as episodic event construction followed by memory refinement. Instead of treating retrieved keyframes as independent visuals, Video-EM employs an LLM as an active memory agent to orchestrate off-the-shelf tools: it first localizes query-relevant moments via multi-grained semantic matching, then groups and segments them into temporally coherent events, and finally encodes each event as a grounded episodic memory with explicit temporal indices and spatio-temporal cues (capturing when, where, what, and involved entities). To further suppress verbosity and noise from imperfect upstream signals, Video-EM integrates a reasoning-driven self-reflection loop that iteratively verifies evidence sufficiency and cross-event consistency, removes redundancy, and adaptively adjusts event granularity. The outcome is a compact yet reliable event timeline -- a minimal but sufficient episodic memory set that can be directly consumed by existing Video-LLMs without additional training or architectural changes.