# HowToCaption: Prompting LLMs to Transform Video Annotations at Scale

arXiv: https://arxiv.org/abs/2310.04900 · HTML: https://mlsanity.com/paper/2310.04900/

## Key facts

- Cited by 34 papers in the map (data through 14 Oct 2026).
- Builds on 62 of its 78 references that are in the map.
- First posted on arXiv 7 Oct 2023.

## Builds on (most cited first, 30 of 62)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision](https://mlsanity.com/paper/2102.05918/) (2021)
- [MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models](https://mlsanity.com/paper/2304.10592/) (2023)
- [Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations](https://mlsanity.com/paper/1602.07332/) (2016)
- [ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks](https://mlsanity.com/paper/1908.02265/) (2019)
- [LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs](https://mlsanity.com/paper/2111.02114/) (2021)
- [LXMERT: Learning Cross-Modality Encoder Representations from Transformers](https://mlsanity.com/paper/1908.07490/) (2019)
- [Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Concepts](https://mlsanity.com/paper/2102.08981/) (2021)
- [Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval](https://mlsanity.com/paper/2104.00650/) (2021)
- [Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models](https://mlsanity.com/paper/2306.05424/) (2023)
- [VL-BERT: Pre-training of Generic Visual-Linguistic Representations](https://mlsanity.com/paper/1908.08530/) (2019)
- [HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clips](https://mlsanity.com/paper/1906.03327/) (2019)
- [VideoBERT: A Joint Model for Video and Language Representation Learning](https://mlsanity.com/paper/1904.01766/) (2019)
- [CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval](https://mlsanity.com/paper/2104.08860/) (2021)
- [Towards Automatic Learning of Procedures from Web Instructional Videos](https://mlsanity.com/paper/1703.09788/) (2017)
- [GIT: A Generative Image-to-text Transformer for Vision and Language](https://mlsanity.com/paper/2205.14100/) (2022)
- [End-to-End Learning of Visual Representations from Uncurated Instructional Videos](https://mlsanity.com/paper/1912.06430/) (2019)
- [InternVid: A Large-scale Video-Text Dataset for Multimodal Understanding and Generation](https://mlsanity.com/paper/2307.06942/) (2023)
- [Unifying Vision-and-Language Tasks via Text Generation](https://mlsanity.com/paper/2102.02779/) (2021)
- [Multi-modal Transformer for Video Retrieval](https://mlsanity.com/paper/2007.10639/) (2020)
- [Text and Code Embeddings by Contrastive Pre-Training](https://mlsanity.com/paper/2201.10005/) (2022)

## Built on by (most cited first, 30 of 34)

- [Direct Preference Optimization of Video Large Multimodal Models from Language Model Reward](https://mlsanity.com/paper/2404.01258/) (2024)
- [E.T. Bench: Towards Open-Ended Event-Level Video-Language Understanding](https://mlsanity.com/paper/2409.18111/) (2024)
- [Towards Natural Language-Guided Drones: GeoText-1652 Benchmark with Spatial Relation Matching](https://mlsanity.com/paper/2311.12751/) (2023)
- [AutoAD III: The Prequel -- Back to the Pixels](https://mlsanity.com/paper/2404.14412/) (2024)
- [VideoAuteur: Towards Long Narrative Video Generation](https://mlsanity.com/paper/2501.06173/) (2025)
- [HierarQ: Task-Aware Hierarchical Q-Former for Enhanced Video Understanding](https://mlsanity.com/paper/2503.08585/) (2025)
- [Shot-by-Shot: Film-Grammar-Aware Training-Free Audio Description Generation](https://mlsanity.com/paper/2504.01020/) (2025)
- [Unlocking Exocentric Video-Language Data for Egocentric Video Representation Learning](https://mlsanity.com/paper/2408.03567/) (2024)
- [Multi-Sentence Grounding for Long-term Instructional Video](https://mlsanity.com/paper/2312.14055/) (2023)
- [Planner3D: LLM-enhanced graph prior meets 3D indoor scene explicit regularization](https://mlsanity.com/paper/2403.12848/) (2024)
- [Chapter-Llama: Efficient Chaptering in Hour-Long Videos with LLMs](https://mlsanity.com/paper/2504.00072/) (2025)
- [Harmful YouTube Video Detection: A Taxonomy of Online Harm and MLLMs as Alternative Annotators](https://mlsanity.com/paper/2411.05854/) (2024)
- [ShowHowTo: Generating Scene-Conditioned Step-by-Step Visual Instructions](https://mlsanity.com/paper/2412.01987/) (2024)
- [VEDIT: Latent Prediction Architecture For Procedural Video Representation Learning](https://mlsanity.com/paper/2410.03478/) (2024)
- [Learning to Localize Actions in Instructional Videos with LLM-Based Multi-Pathway Text-Video Alignment](https://mlsanity.com/paper/2409.16145/) (2024)
- [VidLA: Video-Language Alignment at Scale](https://mlsanity.com/paper/2403.14870/) (2024)
- [Open Vocabulary Multi-Label Video Classification](https://mlsanity.com/paper/2407.09073/) (2024)
- [No Detail Left Behind: Revisiting Self-Retrieval for Fine-Grained Image Captioning](https://mlsanity.com/paper/2409.03025/) (2024)
- [Large-scale Pre-training for Grounded Video Caption Generation](https://mlsanity.com/paper/2503.10781/) (2025)
- [VideoLoom: A Video Large Language Model for Joint Spatial-Temporal Understanding](https://mlsanity.com/paper/2601.07290/) (2026)
- [StreamTTT: Reconciling Real-Time Perception and Long-Term Memory in Streaming VLMs](https://mlsanity.com/paper/2608.13416/) (2026)
- [Learning Skill-Attributes for Transferable Assessment in Video](https://mlsanity.com/paper/2511.13993/) (2025)
- [Unbiasing through Textual Descriptions: Mitigating Representation Bias in Video Benchmarks](https://mlsanity.com/paper/2503.18637/) (2025)
- [X-CoT: Explainable Text-to-Video Retrieval via LLM-based Chain-of-Thought Reasoning](https://mlsanity.com/paper/2509.21559/) (2025)
- [Leveraging Modality Tags for Enhanced Cross-Modal Video Retrieval](https://mlsanity.com/paper/2504.01591/) (2025)
- [A Computational Model of Message Sensation Value in Short Video Multimodal Features that Predicts Sensory and Behavioral Engagement](https://mlsanity.com/paper/2604.19995/) (2026)
- [Grounded Video Caption Generation](https://mlsanity.com/paper/2411.07584/) (2024)
- [Empowering the Deaf and Hard of Hearing Community: Enhancing Video Captions Using Large Language Models](https://mlsanity.com/paper/2412.00342/) (2024)
- [VideoGEM: Training-free Action Grounding in Videos](https://mlsanity.com/paper/2503.20348/) (2025)
- [DynaStride: Dynamic Stride Windowing with MMCoT for Instructional Multi-Scene Captioning](https://mlsanity.com/paper/2510.23907/) (2025)

## Abstract (arXiv)

Instructional videos are a common source for learning text-video or even multimodal representations by leveraging subtitles extracted with automatic speech recognition systems (ASR) from the audio signal in the videos. However, in contrast to human-annotated captions, both speech and subtitles naturally differ from the visual content of the videos and thus provide only noisy supervision. As a result, large-scale annotation-free web video training data remains sub-optimal for training text-video models. In this work, we propose to leverage the capabilities of large language models (LLMs) to obtain high-quality video descriptions aligned with videos at scale. Specifically, we prompt an LLM to create plausible video captions based on ASR subtitles of instructional videos. To this end, we introduce a prompting method that is able to take into account a longer text of subtitles, allowing us to capture the contextual information beyond one single sentence. We further prompt the LLM to generate timestamps for each produced caption based on the timestamps of the subtitles and finally align the generated captions to the video temporally. In this way, we obtain human-style video captions at scale without human supervision. We apply our method to the subtitles of the HowTo100M dataset, creating a new large-scale dataset, HowToCaption. Our evaluation shows that the resulting captions not only significantly improve the performance over many different benchmark datasets for zero-shot text-video retrieval and video captioning, but also lead to a disentangling of textual narration from the audio, boosting the performance in text-video-audio tasks.