# Streaming Dense Video Captioning

arXiv: https://arxiv.org/abs/2404.01297 · HTML: https://mlsanity.com/paper/2404.01297/

## Key facts

- Cited by 82 papers in the map (data through 14 Oct 2026).
- Builds on 55 of its 67 references that are in the map.
- First posted on arXiv 1 Apr 2024.

## Builds on (most cited first, 30 of 55)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [CIDEr: Consensus-based Image Description Evaluation](https://mlsanity.com/paper/1411.5726/) (2014)
- [Language Models as Knowledge Bases?](https://mlsanity.com/paper/1909.01066/) (2019)
- [Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context](https://mlsanity.com/paper/1901.02860/) (2019)
- [Is Space-Time Attention All You Need for Video Understanding?](https://mlsanity.com/paper/2102.05095/) (2021)
- [ViViT: A Video Vision Transformer](https://mlsanity.com/paper/2103.15691/) (2021)
- [CoCa: Contrastive Captioners are Image-Text Foundation Models](https://mlsanity.com/paper/2205.01917/) (2022)
- [Token Merging: Your ViT But Faster](https://mlsanity.com/paper/2210.09461/) (2022)
- [Dense-Captioning Events in Videos](https://mlsanity.com/paper/1705.00754/) (2017)
- [PaLI: A Jointly-Scaled Multilingual Language-Image Model](https://mlsanity.com/paper/2209.06794/) (2022)
- [Towards Automatic Learning of Procedures from Web Instructional Videos](https://mlsanity.com/paper/1703.09788/) (2017)
- [Generating Sequences With Recurrent Neural Networks](https://mlsanity.com/paper/1308.0850/) (2013)
- [MovieChat: From Dense Token to Sparse Memory for Long Video Understanding](https://mlsanity.com/paper/2307.16449/) (2023)
- [GIT: A Generative Image-to-text Transformer for Vision and Language](https://mlsanity.com/paper/2205.14100/) (2022)
- [MOT16: A Benchmark for Multi-Object Tracking](https://mlsanity.com/paper/1603.00831/) (2016)
- [VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking](https://mlsanity.com/paper/2303.16727/) (2023)
- [Tracking without bells and whistles](https://mlsanity.com/paper/1903.05625/) (2019)
- [Towards Real-Time Multi-Object Tracking](https://mlsanity.com/paper/1909.12605/) (2019)
- [Hiera: A Hierarchical Vision Transformer without the Bells-and-Whistles](https://mlsanity.com/paper/2306.00989/) (2023)
- [Vid2Seq: Large-Scale Pretraining of a Visual Language Model for Dense Video Captioning](https://mlsanity.com/paper/2302.14115/) (2023)
- [PaLI-X: On Scaling up a Multilingual Vision and Language Model](https://mlsanity.com/paper/2305.18565/) (2023)
- [Long-Term Feature Banks for Detailed Video Understanding](https://mlsanity.com/paper/1812.05038/) (2018)
- [Memorizing Transformers](https://mlsanity.com/paper/2203.08913/) (2022)
- [End-to-End Dense Video Captioning with Masked Transformer](https://mlsanity.com/paper/1804.00819/) (2018)
- [MeMViT: Memory-Augmented Multiscale Vision Transformer for Efficient Long-Term Video Recognition](https://mlsanity.com/paper/2201.08383/) (2022)

## Built on by (most cited first, 30 of 82)

- [VideoLLM-online: Online Video Large Language Model for Streaming Video](https://mlsanity.com/paper/2406.11816/) (2024)
- [Streaming Long Video Understanding with Large Language Models](https://mlsanity.com/paper/2405.16009/) (2024)
- [AuroraCap: Efficient, Performant Video Detailed Captioning and a New Benchmark](https://mlsanity.com/paper/2410.03051/) (2024)
- [Streaming Video Question-Answering with In-context Video KV-Cache Retrieval](https://mlsanity.com/paper/2503.00540/) (2025)
- [Flash-VStream: Efficient Real-Time Understanding for Long Video Streams](https://mlsanity.com/paper/2506.23825/) (2025)
- [MovieChat+: Question-aware Sparse Memory for Long Video Question Answering](https://mlsanity.com/paper/2404.17176/) (2024)
- [VL-JEPA: Joint Embedding Predictive Architecture for Vision-language](https://mlsanity.com/paper/2512.10942/) (2025)
- [LION-FS: Fast & Slow Video-Language Thinker as Online Video Assistant](https://mlsanity.com/paper/2503.03663/) (2025)
- [OmniMMI: A Comprehensive Multi-modal Interaction Benchmark in Streaming Video Contexts](https://mlsanity.com/paper/2503.22952/) (2025)
- [Perceive Anything: Recognize, Explain, Caption, and Segment Anything in Images and Videos](https://mlsanity.com/paper/2506.05302/) (2025)
- [StreamMind: Unlocking Full Frame Rate Streaming Video Dialogue through Event-Gated Cognition](https://mlsanity.com/paper/2503.06220/) (2025)
- [A Simple Baseline for Streaming Video Understanding](https://mlsanity.com/paper/2604.02317/) (2026)
- [Omni-Captioner: Data Pipeline, Models, and Benchmark for Omni Detailed Perception](https://mlsanity.com/paper/2510.12720/) (2025)
- [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)
- [FAVOR-Bench: A Comprehensive Benchmark for Fine-Grained Video Motion Understanding](https://mlsanity.com/paper/2503.14935/) (2025)
- [Towards Universal Soccer Video Understanding](https://mlsanity.com/paper/2412.01820/) (2024)
- [VideoLLaMB: Long Streaming Video Understanding with Recurrent Memory Bridges](https://mlsanity.com/paper/2409.01071/) (2024)
- [PPLLaVA: Varied Video Sequence Understanding With Prompt Guidance](https://mlsanity.com/paper/2411.02327/) (2024)
- [ViCaS: A Dataset for Combining Holistic and Pixel-level Video Understanding using Captions with Grounded Segmentation](https://mlsanity.com/paper/2412.09754/) (2024)
- [K-Sort Arena: Efficient and Reliable Benchmarking for Generative Models via K-wise Human Preferences](https://mlsanity.com/paper/2408.14468/) (2024)
- [ARGUS: Hallucination and Omission Evaluation in Video-LLMs](https://mlsanity.com/paper/2506.07371/) (2025)
- [LongViTU: Instruction Tuning for Long-Form Video Understanding](https://mlsanity.com/paper/2501.05037/) (2025)
- [Shot-by-Shot: Film-Grammar-Aware Training-Free Audio Description Generation](https://mlsanity.com/paper/2504.01020/) (2025)
- [Seq2Time: Sequential Knowledge Transfer for Video LLM Temporal Grounding](https://mlsanity.com/paper/2411.16932/) (2024)
- [Enrich and Detect: Video Temporal Grounding with Multimodal LLMs](https://mlsanity.com/paper/2510.17023/) (2025)
- [Progress-Aware Video Frame Captioning](https://mlsanity.com/paper/2412.02071/) (2024)
- [MoniTor: Exploiting Large Language Models with Instruction for Online Video Anomaly Detection](https://mlsanity.com/paper/2510.21449/) (2025)
- [Learning Streaming Video Representation via Multitask Training](https://mlsanity.com/paper/2504.20041/) (2025)
- [AdaDrive: Self-Adaptive Slow-Fast System for Language-Grounded Autonomous Driving](https://mlsanity.com/paper/2511.06253/) (2025)

## Abstract (arXiv)

An ideal model for dense video captioning -- predicting captions localized temporally in a video -- should be able to handle long input videos, predict rich, detailed textual descriptions, and be able to produce outputs before processing the entire video. Current state-of-the-art models, however, process a fixed number of downsampled frames, and make a single full prediction after seeing the whole video. We propose a streaming dense video captioning model that consists of two novel components: First, we propose a new memory module, based on clustering incoming tokens, which can handle arbitrarily long videos as the memory is of a fixed size. Second, we develop a streaming decoding algorithm that enables our model to make predictions before the entire video has been processed. Our model achieves this streaming ability, and significantly improves the state-of-the-art on three dense video captioning benchmarks: ActivityNet, YouCook2 and ViTT. Our code is released at https://github.com/google-research/scenic.