# Video ReCap: Recursive Captioning of Hour-Long Videos

arXiv: https://arxiv.org/abs/2402.13250 · HTML: https://mlsanity.com/paper/2402.13250/

## Key facts

- Cited by 89 papers in the map (data through 14 Oct 2026).
- Builds on 51 of its 79 references that are in the map.
- First posted on arXiv 20 Feb 2024.

## Builds on (most cited first, 30 of 51)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [Neural Machine Translation by Jointly Learning to Align and Translate](https://mlsanity.com/paper/1409.0473/) (2014)
- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter](https://mlsanity.com/paper/1910.01108/) (2019)
- [Scaling Instruction-Finetuned Language Models](https://mlsanity.com/paper/2210.11416/) (2022)
- [Sequence to Sequence Learning with Neural Networks](https://mlsanity.com/paper/1409.3215/) (2014)
- [CIDEr: Consensus-based Image Description Evaluation](https://mlsanity.com/paper/1411.5726/) (2014)
- [Is Space-Time Attention All You Need for Video Understanding?](https://mlsanity.com/paper/2102.05095/) (2021)
- [Ego4D: Around the World in 3,000 Hours of Egocentric Video](https://mlsanity.com/paper/2110.07058/) (2021)
- [mPLUG-Owl: Modularization Empowers Large Language Models with Multimodality](https://mlsanity.com/paper/2304.14178/) (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)
- [EgoSchema: A Diagnostic Benchmark for Very Long-form Video Language Understanding](https://mlsanity.com/paper/2308.09126/) (2023)
- [Towards Automatic Learning of Procedures from Web Instructional Videos](https://mlsanity.com/paper/1703.09788/) (2017)
- [ClipCap: CLIP Prefix for Image Captioning](https://mlsanity.com/paper/2111.09734/) (2021)
- [Long-term Recurrent Convolutional Networks for Visual Recognition and Description](https://mlsanity.com/paper/1411.4389/) (2014)
- [InternVideo: General Video Foundation Models via Generative and Discriminative Learning](https://mlsanity.com/paper/2212.03191/) (2022)
- [VATEX: A Large-Scale, High-Quality Multilingual Dataset for Video-and-Language Research](https://mlsanity.com/paper/1904.03493/) (2019)
- [HERO: Hierarchical Encoder for Video+Language Omni-representation Pre-training](https://mlsanity.com/paper/2005.00200/) (2020)
- [COIN: A Large-scale Dataset for Comprehensive Instructional Video Analysis](https://mlsanity.com/paper/1903.02874/) (2019)
- [Assembly101: A Large-Scale Multi-View Video Dataset for Understanding Procedural Activities](https://mlsanity.com/paper/2203.14712/) (2022)
- [Vid2Seq: Large-Scale Pretraining of a Visual Language Model for Dense Video Captioning](https://mlsanity.com/paper/2302.14115/) (2023)
- [UniVL: A Unified Video and Language Pre-Training Model for Multimodal Understanding and Generation](https://mlsanity.com/paper/2002.06353/) (2020)
- [Egocentric Video-Language Pretraining](https://mlsanity.com/paper/2206.01670/) (2022)
- [Zero-Shot Video Question Answering via Frozen Bidirectional Language Models](https://mlsanity.com/paper/2206.08155/) (2022)
- [Learning Video Representations from Large Language Models](https://mlsanity.com/paper/2212.04501/) (2022)
- [Cross-task weakly supervised learning from instructional videos](https://mlsanity.com/paper/1903.08225/) (2019)

## Built on by (most cited first, 30 of 89)

- [LLaVA-Video: Video Instruction Tuning With Synthetic Data](https://mlsanity.com/paper/2410.02713/) (2024)
- [VideoTree: Adaptive Tree-based Video Representation for LLM Reasoning on Long Videos](https://mlsanity.com/paper/2405.19209/) (2024)
- [VideoChat-Flash: Hierarchical Compression for Long-Context Video Modeling](https://mlsanity.com/paper/2501.00574/) (2024)
- [InternLM-XComposer-2.5: A Versatile Large Vision Language Model Supporting Long-Contextual Input and Output](https://mlsanity.com/paper/2407.03320/) (2024)
- [Streaming Long Video Understanding with Large Language Models](https://mlsanity.com/paper/2405.16009/) (2024)
- [Audio Flamingo 2: An Audio-Language Model with Long-Audio Understanding and Expert Reasoning Abilities](https://mlsanity.com/paper/2503.03983/) (2025)
- [Streaming Video Question-Answering with In-context Video KV-Cache Retrieval](https://mlsanity.com/paper/2503.00540/) (2025)
- [HourVideo: 1-Hour Video-Language Understanding](https://mlsanity.com/paper/2411.04998/) (2024)
- [Seeing, Listening, Remembering, and Reasoning: A Multimodal Agent with Long-Term Memory](https://mlsanity.com/paper/2508.09736/) (2025)
- [EgoLife: Towards Egocentric Life Assistant](https://mlsanity.com/paper/2503.03803/) (2025)
- [Holmes-VAU: Towards Long-term Video Anomaly Understanding at Any Granularity](https://mlsanity.com/paper/2412.06171/) (2024)
- [Eagle 2.5: Boosting Long-Context Post-Training for Frontier Vision-Language Models](https://mlsanity.com/paper/2504.15271/) (2025)
- [Language Repository for Long Video Understanding](https://mlsanity.com/paper/2403.14622/) (2024)
- [InternLM-XComposer2.5-OmniLive: A Comprehensive Multimodal System for Long-term Streaming Video and Audio Interactions](https://mlsanity.com/paper/2412.09596/) (2024)
- [VideoITG: Multimodal Video Understanding with Instructed Temporal Grounding](https://mlsanity.com/paper/2507.13353/) (2025)
- [LiveStar: Live Streaming Assistant for Real-World Online Video Understanding](https://mlsanity.com/paper/2511.05299/) (2025)
- [BIMBA: Selective-Scan Compression for Long-Range Video Question Answering](https://mlsanity.com/paper/2503.09590/) (2025)
- [Modeling Fine-Grained Hand-Object Dynamics for Egocentric Video Representation Learning](https://mlsanity.com/paper/2503.00986/) (2025)
- [Video Summarization with Large Language Models](https://mlsanity.com/paper/2504.11199/) (2025)
- [StoryTeller: Improving Long Video Description through Global Audio-Visual Character Identification](https://mlsanity.com/paper/2411.07076/) (2024)
- [X-LeBench: A Benchmark for Extremely Long Egocentric Video Understanding](https://mlsanity.com/paper/2501.06835/) (2025)
- [Do Language Models Understand Time?](https://mlsanity.com/paper/2412.13845/) (2024)
- [Shot-by-Shot: Film-Grammar-Aware Training-Free Audio Description Generation](https://mlsanity.com/paper/2504.01020/) (2025)
- [Propose, Assess, Search: Harnessing LLMs for Goal-Oriented Planning in Instructional Videos](https://mlsanity.com/paper/2409.20557/) (2024)
- [Progress-Aware Video Frame Captioning](https://mlsanity.com/paper/2412.02071/) (2024)
- [What Is That Talk About? A Video-to-Text Summarization Dataset for Scientific Presentations](https://mlsanity.com/paper/2502.08279/) (2025)
- [VideoMiner: Iteratively Grounding Key Frames of Hour-Long Videos via Tree-based Group Relative Policy Optimization](https://mlsanity.com/paper/2510.06040/) (2025)
- [Any2Caption:Interpreting Any Condition to Caption for Controllable Video Generation](https://mlsanity.com/paper/2503.24379/) (2025)
- [ZoomV: Temporal Zoom-in for Efficient Long Video Understanding](https://mlsanity.com/paper/2504.01407/) (2025)
- [EGOILLUSION: Benchmarking Hallucinations in Egocentric Video Understanding](https://mlsanity.com/paper/2508.12687/) (2025)

## Abstract (arXiv)

Most video captioning models are designed to process short video clips of few seconds and output text describing low-level visual concepts (e.g., objects, scenes, atomic actions). However, most real-world videos last for minutes or hours and have a complex hierarchical structure spanning different temporal granularities. We propose Video ReCap, a recursive video captioning model that can process video inputs of dramatically different lengths (from 1 second to 2 hours) and output video captions at multiple hierarchy levels. The recursive video-language architecture exploits the synergy between different video hierarchies and can process hour-long videos efficiently. We utilize a curriculum learning training scheme to learn the hierarchical structure of videos, starting from clip-level captions describing atomic actions, then focusing on segment-level descriptions, and concluding with generating summaries for hour-long videos. Furthermore, we introduce Ego4D-HCap dataset by augmenting Ego4D with 8,267 manually collected long-range video summaries. Our recursive model can flexibly generate captions at different hierarchy levels while also being useful for other complex video understanding tasks, such as VideoQA on EgoSchema. Data, code, and models are available at: https://sites.google.com/view/vidrecap