# Memory-enhanced Retrieval Augmentation for Long Video Understanding

arXiv: https://arxiv.org/abs/2503.09149 · HTML: https://mlsanity.com/paper/2503.09149/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal RAG, one of 15 directions in Retrieval-augmented generation.
- Builds on 44 of its 50 references that are in the map.
- First posted on arXiv 12 Mar 2025.

## Placed in

- Retrieval-augmented generation / [Multimodal RAG](https://mlsanity.com/rag/multimodal-rag/)

## Builds on (most cited first, 30 of 44)

- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://mlsanity.com/paper/2403.05530/) (2024)
- [MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models](https://mlsanity.com/paper/2304.10592/) (2023)
- [Retrieval-Augmented Generation for Large Language Models: A Survey](https://mlsanity.com/paper/2312.10997/) (2023)
- [Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis](https://mlsanity.com/paper/2405.21075/) (2024)
- [Video-LLaVA: Learning United Visual Representation by Alignment Before Projection](https://mlsanity.com/paper/2311.10122/) (2023)
- [ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools](https://mlsanity.com/paper/2406.12793/) (2024)
- [MVBench: A Comprehensive Multi-modal Video Understanding Benchmark](https://mlsanity.com/paper/2311.17005/) (2023)
- [Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models](https://mlsanity.com/paper/2306.05424/) (2023)
- [How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites](https://mlsanity.com/paper/2404.16821/) (2024)
- [VideoChat: Chat-Centric Video Understanding](https://mlsanity.com/paper/2305.06355/) (2023)
- [NExT-QA:Next Phase of Question-Answering to Explaining Temporal Actions](https://mlsanity.com/paper/2105.08276/) (2021)
- [VILA: On Pre-training for Visual Language Models](https://mlsanity.com/paper/2312.07533/) (2023)
- [ActivityNet-QA: A Dataset for Understanding Complex Web Videos via Question Answering](https://mlsanity.com/paper/1906.02467/) (2019)
- [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)
- [Precise Zero-Shot Dense Retrieval without Relevance Labels](https://mlsanity.com/paper/2212.10496/) (2022)
- [Long Context Transfer from Language to Vision](https://mlsanity.com/paper/2406.16852/) (2024)
- [A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Models](https://mlsanity.com/paper/2405.06211/) (2024)
- [TimeChat: A Time-sensitive Multimodal Large Language Model for Long Video Understanding](https://mlsanity.com/paper/2312.02051/) (2023)
- [ShareGPT4Video: Improving Video Understanding and Generation with Better Captions](https://mlsanity.com/paper/2406.04325/) (2024)
- [LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment](https://mlsanity.com/paper/2310.01852/) (2023)
- [Retrieval-Augmented Generation for AI-Generated Content: A Survey](https://mlsanity.com/paper/2402.19473/) (2024)
- [Large Language Models for Information Retrieval: A Survey](https://mlsanity.com/paper/2308.07107/) (2023)
- [PLLaVA : Parameter-free LLaVA Extension from Images to Videos for Video Dense Captioning](https://mlsanity.com/paper/2404.16994/) (2024)
- [LongVILA: Scaling Long-Context Visual Language Models for Long Videos](https://mlsanity.com/paper/2408.10188/) (2024)
- [Valley: Video Assistant with Large Language model Enhanced abilitY](https://mlsanity.com/paper/2306.07207/) (2023)

## Built on by (most cited first, 17 of 17)

- [Video-XL-2: Towards Very Long-Video Understanding Through Task-Aware KV Sparsification](https://mlsanity.com/paper/2506.19225/) (2025)
- [VideoLucy: Deep Memory Backtracking for Long Video Understanding](https://mlsanity.com/paper/2510.12422/) (2025)
- [Vid-SME: Membership Inference Attacks against Large Video Understanding Models](https://mlsanity.com/paper/2506.03179/) (2025)
- [See&Trek: Training-Free Spatial Prompting for Multimodal Large Language Model](https://mlsanity.com/paper/2509.16087/) (2025)
- [When Semantics Mislead Vision: Mitigating Large Multimodal Models Hallucinations in Scene Text Spotting and Understanding](https://mlsanity.com/paper/2506.05551/) (2025)
- [VidText: Towards Comprehensive Evaluation for Video Text Understanding](https://mlsanity.com/paper/2505.22810/) (2025)
- [LongVideo-R1: Smart Navigation for Low-cost Long Video Understanding](https://mlsanity.com/paper/2602.20913/) (2026)
- [Video-R4: Reinforcing Text-Rich Video Reasoning with Visual Rumination](https://mlsanity.com/paper/2511.17490/) (2025)
- [Persistent Visual Memory: Sustaining Perception for Deep Generation in LVLMs](https://mlsanity.com/paper/2605.00814/) (2026)
- [Watch, Remember, Reason: Human-View Video Understanding with MLLMs](https://mlsanity.com/paper/2606.07433/) (2026)
- [A.I.R.: Enabling Adaptive, Iterative, and Reasoning-based Frame Selection For Video Question Answering](https://mlsanity.com/paper/2510.04428/) (2025)
- [SuperMemory-VQA: An Egocentric Visual Question-Answering Benchmark for Long-Horizon Memory](https://mlsanity.com/paper/2606.00825/) (2026)
- [Towards Effective Long Video Understanding of Multimodal Large Language Models via One-shot Clip Retrieval](https://mlsanity.com/paper/2512.08410/) (2025)
- [ForeSea: AI Forensic Search with Multi-modal Queries for Video Surveillance](https://mlsanity.com/paper/2603.22872/) (2026)
- [Seeing the Scene Matters: Revealing Forgetting in Video Understanding Models with a Scene-Aware Long-Video Benchmark](https://mlsanity.com/paper/2603.27259/) (2026)
- [MultiVENT-Raw: A Benchmark for Retrieval and Reasoning over Raw Videos](https://mlsanity.com/paper/2609.28437/) (2026)
- [VideoEvolve: Co-Evolving Memory and Retrieval for Long Video Understanding](https://mlsanity.com/paper/2610.10183/) (2026)

## Abstract (arXiv)

Efficient long-video understanding~(LVU) remains a challenging task in computer vision. Current long-context vision-language models~(LVLMs) suffer from information loss due to compression and brute-force downsampling. While retrieval-augmented generation (RAG) methods mitigate this issue, their applicability is limited due to explicit query dependency. To overcome this challenge, we introduce a novel memory-enhanced RAG-based approach called MemVid, which is inspired by the cognitive memory of human beings. Our approach operates in four basic steps: 1) memorizing holistic video information, 2) reasoning about the task's information needs based on memory, 3) retrieving critical moments based on the information needs, and 4) focusing on the retrieved moments to produce the final answer. To enhance the system's memory-grounded reasoning capabilities while achieving optimal end-to-end performance, we propose a curriculum learning strategy. This approach begins with supervised learning on well-annotated reasoning results, then progressively explores and reinforces more plausible reasoning outcomes through reinforcement learning. We perform extensive evaluations on popular LVU benchmarks, including MLVU, VideoMME and LVBench. In our experiments, MemVid demonstrates superior efficiency and effectiveness compared to both LVLMs and RAG methods.