# Hierarchical Memory for Long Video QA

arXiv: https://arxiv.org/abs/2407.00603 · HTML: https://mlsanity.com/paper/2407.00603/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 22 references that are in the map.
- First posted on arXiv 30 Jun 2024.

## Builds on (most cited first, 18 of 18)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [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)
- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models](https://mlsanity.com/paper/2306.05424/) (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)
- [Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding](https://mlsanity.com/paper/2311.08046/) (2023)
- [Flash-VStream: Memory-Based Real-Time Understanding for Long Video Streams](https://mlsanity.com/paper/2406.08085/) (2024)
- [MotionLCM: Real-time Controllable Motion Generation via Latent Consistency Model](https://mlsanity.com/paper/2404.19759/) (2024)
- [VoCo-LLaMA: Towards Vision Compression with Large Language Models](https://mlsanity.com/paper/2406.12275/) (2024)
- [Vista-LLaMA: Reducing Hallucination in Video Language Models via Equal Distance to Visual Tokens](https://mlsanity.com/paper/2312.08870/) (2023)
- [ManiCM: Real-time 3D Diffusion Policy via Consistency Model for Robotic Manipulation](https://mlsanity.com/paper/2406.01586/) (2024)
- [VLMixer: Unpaired Vision-Language Pre-training via Cross-Modal CutMix](https://mlsanity.com/paper/2206.08919/) (2022)
- [Learning Quality-aware Dynamic Memory for Video Object Segmentation](https://mlsanity.com/paper/2207.07922/) (2022)
- [Universal Segmentation at Arbitrary Granularity with Language Instruction](https://mlsanity.com/paper/2312.01623/) (2023)
- [Narrative Action Evaluation with Prompt-Guided Multimodal Interaction](https://mlsanity.com/paper/2404.14471/) (2024)

## Built on by (most cited first, 9 of 9)

- [VLA-RL: Towards Masterful and General Robotic Manipulation with Scalable Reinforcement Learning](https://mlsanity.com/paper/2505.18719/) (2025)
- [Flash-VStream: Efficient Real-Time Understanding for Long Video Streams](https://mlsanity.com/paper/2506.23825/) (2025)
- [HierarQ: Task-Aware Hierarchical Q-Former for Enhanced Video Understanding](https://mlsanity.com/paper/2503.08585/) (2025)
- [Thinking With Bounding Boxes: Enhancing Spatio-Temporal Video Grounding via Reinforcement Fine-Tuning](https://mlsanity.com/paper/2511.21375/) (2025)
- [ScoreHOI: Physically Plausible Reconstruction of Human-Object Interaction via Score-Guided Diffusion](https://mlsanity.com/paper/2509.07920/) (2025)
- [Stepping Out of Similar Semantic Space for Open-Vocabulary Segmentation](https://mlsanity.com/paper/2506.16058/) (2025)
- [An Efficient Streaming Video Understanding Framework with Agentic Control](https://mlsanity.com/paper/2605.17921/) (2026)
- [M3: 3D-Spatial MultiModal Memory](https://mlsanity.com/paper/2503.16413/) (2025)
- [VTI-CoT: Visual-Textual Interleaved Chain of Thought for Video Reasoning](https://mlsanity.com/paper/2606.05736/) (2026)

## Abstract (arXiv)

This paper describes our champion solution to the LOVEU Challenge @ CVPR'24, Track 1 (Long Video VQA). Processing long sequences of visual tokens is computationally expensive and memory-intensive, making long video question-answering a challenging task. The key is to compress visual tokens effectively, reducing memory footprint and decoding latency, while preserving the essential information for accurate question-answering. We adopt a hierarchical memory mechanism named STAR Memory, proposed in Flash-VStream, that is capable of processing long videos with limited GPU memory (VRAM). We further utilize the video and audio data of MovieChat-1K training set to fine-tune the pretrained weight released by Flash-VStream, achieving 1st place in the challenge. Code is available at project homepage https://invinciblewyq.github.io/vstream-page .