iBet uBet web content aggregator. Adding the entire web to your favor.
iBet uBet web content aggregator. Adding the entire web to your favor.



Link to original content: https://unpaywall.org/10.1007/978-3-031-72992-8_1
HowToCaption: Prompting LLMs to Transform Video Annotations at Scale | SpringerLink
Skip to main content
Springer Nature Link
Log in

HowToCaption: Prompting LLMs to Transform Video Annotations at Scale

  • Conference paper
  • First Online:
Computer Vision – ECCV 2024 (ECCV 2024)

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 15114))

Included in the following conference series:

Abstract

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. All data and code is available at https://github.com/ninatu/howtocaption.

N. Shvetsova and A. Kukleva—Equal contribution.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 64.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 79.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

References

  1. Abu-El-Haija, S., et al.: YouTube-8m: a large-scale video classification benchmark. arXiv preprint arXiv:1609.08675 (2016)

  2. Afouras, T., Mavroudi, E., Nagarajan, T., Wang, H., Torresani, L.: HT-step: aligning instructional articles with how-to videos. In: NeurIPS, vol. 36 (2024)

    Google Scholar 

  3. Amrani, E., Ben-Ari, R., Rotman, D., Bronstein, A.: Noise estimation using density estimation for self-supervised multimodal learning. In: AAAI (2021)

    Google Scholar 

  4. Bain, M., Nagrani, A., Varol, G., Zisserman, A.: Frozen in time: a joint video and image encoder for end-to-end retrieval. In: ICCV (2021)

    Google Scholar 

  5. Chang, T.A., Bergen, B.K.: Language model behavior: a comprehensive survey. arXiv preprint arXiv:2303.11504 (2023)

  6. Changpinyo, S., Sharma, P., Ding, N., Soricut, R.: Conceptual 12m: pushing web-scale image-text pre-training to recognize long-tail visual concepts. In: CVPR (2021)

    Google Scholar 

  7. Chen, B., et al.: Multimodal clustering networks for self-supervised learning from unlabeled videos. In: ICCV (2021)

    Google Scholar 

  8. Chen, D., Dolan, W.B.: Collecting highly parallel data for paraphrase evaluation. In: ACL (2011)

    Google Scholar 

  9. Chen, S., et al.: Vast: a vision-audio-subtitle-text omni-modality foundation model and dataset. In: NeurIPS, vol. 36 (2023)

    Google Scholar 

  10. Chiang, W.L., et al.: Vicuna: an open-source chatbot impressing GPT-4 with 90%* ChatGPT quality. Large Model Syst. Organ. (2023)

    Google Scholar 

  11. Cho, J., Lei, J., Tan, H., Bansal, M.: Unifying vision-and-language tasks via text generation. In: ICML (2021)

    Google Scholar 

  12. Desai, K., Johnson, J.: Virtex: learning visual representations from textual annotations. In: CVPR (2021)

    Google Scholar 

  13. Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: NAACL (2019)

    Google Scholar 

  14. Gabeur, V., Sun, C., Alahari, K., Schmid, C.: Multi-modal transformer for video retrieval. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12349, pp. 214–229. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58548-8_13

    Chapter  Google Scholar 

  15. Ghadiyaram, D., Tran, D., Mahajan, D.: Large-scale weakly-supervised pre-training for video action recognition. In: CVPR (2019)

    Google Scholar 

  16. Han, T., Xie, W., Zisserman, A.: Temporal alignment networks for long-term video. In: CVPR (2022)

    Google Scholar 

  17. Hou, S., Pan, X., Loy, C.C., Wang, Z., Lin, D.: Learning a unified classifier incrementally via rebalancing. In: CVPR (2019)

    Google Scholar 

  18. Jia, C., et al.: Scaling up visual and vision-language representation learning with noisy text supervision. In: ICML (2021)

    Google Scholar 

  19. Koupaee, M., Wang, W.Y.: Wikihow: a large scale text summarization dataset. arXiv preprint arXiv:1810.09305 (2018)

  20. Krishna, R., et al.: Visual genome: connecting language and vision using crowdsourced dense image annotations. IJCV (2017)

    Google Scholar 

  21. Li, J., Li, D., Savarese, S., Hoi, S.: Blip-2: bootstrapping language-image pre-training with frozen image encoders and large language models. In: ICML (2023)

    Google Scholar 

  22. Li, J., Li, D., Xiong, C., Hoi, S.: Blip: bootstrapping language-image pre-training for unified vision-language understanding and generation. In: ICML (2022)

    Google Scholar 

  23. Li, Z., Chen, Q., Han, T., Zhang, Y., Wang, Y., Xie, W.: A strong baseline for temporal video-text alignment. arXiv preprint arXiv:2312.14055 (2023)

  24. Lialin, V., Rawls, S., Chan, D., Ghosh, S., Rumshisky, A., Hamza, W.: Scalable and accurate self-supervised multimodal representation learning without aligned video and text data. In: WACV (2023)

    Google Scholar 

  25. Lin, K., et al.: SwinBERT: end-to-end transformers with sparse attention for video captioning. In: CVPR (2022)

    Google Scholar 

  26. Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740–755. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-10602-1_48

    Chapter  Google Scholar 

  27. Lin, X., Petroni, F., Bertasius, G., Rohrbach, M., Chang, S.F., Torresani, L.: Learning to recognize procedural activities with distant supervision. In: CVPR (2022)

    Google Scholar 

  28. Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. In: NeurIPS, vol. 36 (2023)

    Google Scholar 

  29. Lu, J., Batra, D., Parikh, D., Lee, S.: VilBERT: pretraining task-agnostic visiolinguistic representations for vision-and-language tasks. In: NeurIPS (2019)

    Google Scholar 

  30. Luo, H., Ji, L., Zhong, M., Chen, Y., Lei, W., Duan, N., Li, T.: CLIP4clip: an empirical study of clip for end to end video clip retrieval and captioning. Neurocomputing (2022)

    Google Scholar 

  31. Maaz, M., Rasheed, H., Khan, S., Khan, F.S.: Video-ChatGPT: towards detailed video understanding via large vision and language models. arXiv preprint arXiv:2306.05424 (2023)

  32. Miech, A., Alayrac, J.B., Smaira, L., Laptev, I., Sivic, J., Zisserman, A.: End-to-end learning of visual representations from uncurated instructional videos. In: CVPR (2020)

    Google Scholar 

  33. Miech, A., Zhukov, D., Alayrac, J.B., Tapaswi, M., Laptev, I., Sivic, J.: Howto100m: learning a text-video embedding by watching hundred million narrated video clips. In: ICCV (2019)

    Google Scholar 

  34. Nagrani, A., et al.: Learning audio-video modalities from image captions. In: Avidan, S., Brostow, G., Cissé, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13674, pp. 407–426. Springer, Cham (2022). https://doi.org/10.1007/978-3-031-19781-9_24

    Chapter  Google Scholar 

  35. Neelakantan, A., et al.: Text and code embeddings by contrastive pre-training. arXiv preprint arXiv:2201.10005 (2022)

  36. van den Oord, A., Li, Y., Vinyals, O.: Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748 (2018)

  37. Ordonez, V., Kulkarni, G., Berg, T.: Im2text: describing images using 1 million captioned photographs. In: NeurIPS (2011)

    Google Scholar 

  38. Portillo-Quintero, J.A., Ortiz-Bayliss, J.C., Terashima-Marín, H.: A straightforward framework for video retrieval using clip. In: Pattern Recognition: 13th Mexican Conference (2021)

    Google Scholar 

  39. Radford, A., et al.: Learning transferable visual models from natural language supervision. In: ICML (2021)

    Google Scholar 

  40. Radford, A., Kim, J.W., Xu, T., Brockman, G., McLeavey, C., Sutskever, I.: Robust speech recognition via large-scale weak supervision. In: ICML (2023)

    Google Scholar 

  41. Radford, A., et al.: Language models are unsupervised multitask learners. OpenAI Blog (2019)

    Google Scholar 

  42. Raffel, C., et al.: Exploring the limits of transfer learning with a unified text-to-text transformer. JMLR (2020)

    Google Scholar 

  43. Rohrbach, A., Rohrbach, M., Schiele, B.: The long-short story of movie description. In: Gall, J., Gehler, P., Leibe, B. (eds.) GCPR 2015. LNCS, vol. 9358, pp. 209–221. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-24947-6_17

    Chapter  Google Scholar 

  44. Rouditchenko, A., et al.: AVLnet: learning audio-visual language representations from instructional videos. In: Interspeech (2021)

    Google Scholar 

  45. Schuhmann, C., et al.: LAION-400m: open dataset of clip-filtered 400 million image-text pairs. arXiv preprint arXiv:2111.02114 (2021)

  46. Seo, P.H., Nagrani, A., Arnab, A., Schmid, C.: End-to-end generative pretraining for multimodal video captioning. In: CVPR (2022)

    Google Scholar 

  47. Shvetsova, N., et al.: Everything at once-multi-modal fusion transformer for video retrieval. In: CVPR (2022)

    Google Scholar 

  48. Stroud, J.C., et al.: Learning video representations from textual web supervision. arXiv preprint arXiv:2007.14937 (2020)

  49. Su, W., et al.: VL-BERT: pre-training of generic visual-linguistic representations. In: ICLR (2020)

    Google Scholar 

  50. Sun, C., Myers, A., Vondrick, C., Murphy, K., Schmid, C.: VideoBERT: a joint model for video and language representation learning. In: ICCV (2019)

    Google Scholar 

  51. Tan, H., Bansal, M.: LXMERT: learning cross-modality encoder representations from transformers. In: EMNLP (2019)

    Google Scholar 

  52. Tang, M., Wang, Z., Liu, Z., Rao, F., Li, D., Li, X.: Clip4caption: clip for video caption. In: ACMMM (2021)

    Google Scholar 

  53. Taori, R., et al: Alpaca: a strong, replicable instruction-following model. Stanford Center for Research on Foundation Models (2023)

    Google Scholar 

  54. Touvron, H., et al.: Llama: open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)

  55. Wang, J., et al.: GIT: a generative image-to-text transformer for vision and language. arXiv preprint arXiv:2205.14100 (2022)

  56. Wang, Y., et al.: InternVid: a large-scale video-text dataset for multimodal understanding and generation. arXiv preprint arXiv:2307.06942 (2023)

  57. Xu, H., et al.: mPLUG-2: a modularized multi-modal foundation model across text, image and video. arXiv preprint arXiv:2302.00402 (2023)

  58. Xu, J., Mei, T., Yao, T., Rui, Y.: MSR-VTT: a large video description dataset for bridging video and language. In: CVPR (2016)

    Google Scholar 

  59. Xue, H., et al.: Advancing high-resolution video-language representation with large-scale video transcriptions. In: CVPR (2022)

    Google Scholar 

  60. Yan, S., et al.: Video-text modeling with zero-shot transfer from contrastive captioners. arXiv preprint arXiv:2212.04979 (2022)

  61. Yang, A., Nagrani, A., Laptev, I., Sivic, J., Schmid, C.: Vidchapters-7m: video chapters at scale. In: NeurIPS, vol. 36 (2024)

    Google Scholar 

  62. Yang, A., et al.: Vid2seq: large-scale pretraining of a visual language model for dense video captioning. In: CVPR (2023)

    Google Scholar 

  63. Ye, Q., et al.: Hitea: hierarchical temporal-aware video-language pre-training. In: ICCV, pp. 15405–15416 (2023)

    Google Scholar 

  64. Zala, A., et al.: Hierarchical video-moment retrieval and step-captioning. In: CVPR (2023)

    Google Scholar 

  65. Zellers, R., et al.: Merlot: multimodal neural script knowledge models. In: NeurIPS (2021)

    Google Scholar 

  66. Zhao, Y., Misra, I., Krähenbühl, P., Girdhar, R.: Learning video representations from large language models. In: CVPR (2023)

    Google Scholar 

  67. Zhou, L., Xu, C., Corso, J.: Towards automatic learning of procedures from web instructional videos. In: AAAI (2018)

    Google Scholar 

  68. Zhu, D., Chen, J., Shen, X., Li, X., Elhoseiny, M.: MiniGPT-4: enhancing vision-language understanding with advanced large language models. arXiv preprint arXiv:2304.10592 (2023)

Download references

Acknowledgements

Nina Shvetsova is supported in part by the German Federal Ministry of Education and Research (BMBF) project STCL - 01IS22067.

Author information

Authors and Affiliations

  1. Goethe University Frankfurt, Frankfurt, Germany

    Nina Shvetsova & Hilde Kuehne

  2. MPI for Informatics, SIC, Saarbrücken, Germany

    Nina Shvetsova, Anna Kukleva, Xudong Hong & Bernt Schiele

  3. University of Bonn, Bonn, Germany

    Nina Shvetsova & Hilde Kuehne

  4. University of Oxford, Oxford, UK

    Christian Rupprecht

  5. MIT-IBM Watson AI Lab, Cambridge, USA

    Hilde Kuehne

  6. Saarland University, Saarbrücken, Germany

    Xudong Hong

Authors
  1. Nina Shvetsova
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Anna Kukleva
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Xudong Hong
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Christian Rupprecht
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Bernt Schiele
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Hilde Kuehne
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Nina Shvetsova .

Editor information

Editors and Affiliations

  1. University of Birmingham, Birmingham, UK

    Aleš Leonardis

  2. University of Trento, Trento, Italy

    Elisa Ricci

  3. Technical University of Darmstadt, Darmstadt, Hessen, Germany

    Stefan Roth

  4. Princeton University, Palo Alto, CA, USA

    Olga Russakovsky

  5. Czech Technical University in Prague, Prague, Czech Republic

    Torsten Sattler

  6. École des Ponts ParisTech, Marne-la-Vallée, France

    Gül Varol

1 Electronic supplementary material

Below is the link to the electronic supplementary material.

Supplementary material 1 (pdf 3146 KB)

Rights and permissions

Reprints and permissions

Copyright information

© 2025 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Shvetsova, N., Kukleva, A., Hong, X., Rupprecht, C., Schiele, B., Kuehne, H. (2025). HowToCaption: Prompting LLMs to Transform Video Annotations at Scale. In: Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T., Varol, G. (eds) Computer Vision – ECCV 2024. ECCV 2024. Lecture Notes in Computer Science, vol 15114. Springer, Cham. https://doi.org/10.1007/978-3-031-72992-8_1

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-72992-8_1

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-72991-1

  • Online ISBN: 978-3-031-72992-8

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation