# Live Video Captioning

arXiv: https://arxiv.org/abs/2406.14206 · HTML: https://mlsanity.com/paper/2406.14206/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 53 references that are in the map.
- First posted on arXiv 20 Jun 2024.

## Builds on (most cited first, 21 of 21)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deformable DETR: Deformable Transformers for End-to-End Object Detection](https://mlsanity.com/paper/2010.04159/) (2020)
- [Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regression](https://mlsanity.com/paper/1902.09630/) (2019)
- [Dense-Captioning Events in Videos](https://mlsanity.com/paper/1705.00754/) (2017)
- [VATEX: A Large-Scale, High-Quality Multilingual Dataset for Video-and-Language Research](https://mlsanity.com/paper/1904.03493/) (2019)
- [Vid2Seq: Large-Scale Pretraining of a Visual Language Model for Dense Video Captioning](https://mlsanity.com/paper/2302.14115/) (2023)
- [End-to-End Dense Video Captioning with Masked Transformer](https://mlsanity.com/paper/1804.00819/) (2018)
- [End-to-End Dense Video Captioning with Parallel Decoding](https://mlsanity.com/paper/2108.07781/) (2021)
- [Multi-modal Dense Video Captioning](https://mlsanity.com/paper/2003.07758/) (2020)
- [RED: Reinforced Encoder-Decoder Networks for Action Anticipation](https://mlsanity.com/paper/1707.04818/) (2017)
- [TSP: Temporally-Sensitive Pretraining of Video Encoders for Localization Tasks](https://mlsanity.com/paper/2011.11479/) (2020)
- [Online Action Detection](https://mlsanity.com/paper/1604.06506/) (2016)
- [Bidirectional Attentive Fusion with Context Gating for Dense Video Captioning](https://mlsanity.com/paper/1804.00100/) (2018)
- [Jointly Localizing and Describing Events for Dense Video Captioning](https://mlsanity.com/paper/1804.08274/) (2018)
- [Streamlined Dense Video Captioning](https://mlsanity.com/paper/1904.03870/) (2019)
- [Move Forward and Tell: A Progressive Generator of Video Descriptions](https://mlsanity.com/paper/1807.10018/) (2018)
- [Online Human Action Detection using Joint Classification-Regression Recurrent Neural Networks](https://mlsanity.com/paper/1604.05633/) (2016)
- [The ActivityNet Large-Scale Activity Recognition Challenge 2018 Summary](https://mlsanity.com/paper/1808.03766/) (2018)
- [Rethinking Online Action Detection in Untrimmed Videos: A Novel Online Evaluation Protocol](https://mlsanity.com/paper/2003.12041/) (2020)
- [Optimizing Latency for Online Video CaptioningUsing Audio-Visual Transformers](https://mlsanity.com/paper/2108.02147/) (2021)
- [Syntax Customized Video Captioning by Imitating Exemplar Sentences](https://mlsanity.com/paper/2112.01062/) (2021)

## Built on by (most cited first, 2 of 2)

- [Speak While Watching: Unleashing TRUE Real-Time Video Understanding Capability of Multimodal Large Language Models](https://mlsanity.com/paper/2601.06843/) (2026)
- [NBA_Streaming: A Large-Scale Benchmark for Fine-Grained Basketball Commentary Generation in Continuous Streams](https://mlsanity.com/paper/2608.09200/) (2026)

## Abstract (arXiv)

Dense video captioning involves detecting and describing events within video sequences. Traditional methods operate in an offline setting, assuming the entire video is available for analysis. In contrast, in this work we introduce a groundbreaking paradigm: Live Video Captioning (LVC), where captions must be generated for video streams in an online manner. This shift brings unique challenges, including processing partial observations of the events and the need for a temporal anticipation of the actions. We formally define the novel problem of LVC and propose innovative evaluation metrics specifically designed for this online scenario, demonstrating their advantages over traditional metrics. To address the novel complexities of LVC, we present a new model that combines deformable transformers with temporal filtering, enabling effective captioning over video streams. Extensive experiments on the ActivityNet Captions dataset validate the proposed approach, showcasing its superior performance in the LVC setting compared to state-of-the-art offline methods. To foster further research, we provide the results of our model and an evaluation toolkit with the new metrics integrated at: https://github.com/gramuah/lvc.