EUVIMEDEUVIMED entdecken
Crossref

UVLM: Benchmarking Video Language Model for Underwater World Understanding

Xizhe Xue, Yang Zhou, Dawei Yan, Lijie Tao, Junjie Li, Ying Li, Haokui Zhang, Rong Xiao

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (14) · 11532-11540

DOI: 10.1609/aaai.v40i14.38136 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Xizhe Xue und 7 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Recently, video-language models (VidLMs) have gained widespread attention and adoption. However, existing works primarily focus on terrestrial scenarios, overlooking the highly demanding application needs of underwater observation. To overcome this gap, we introduce UVLM, an under water observation benchmark which is build through a collaborative approach combining human expertise and AI models. To ensure data quality, we have conducted in-depth considerations from multiple perspectives. First, to address the unique challenges of underwater environments, we selected videos that represent typical underwater challenges including light variations, water turbidity, and diverse viewing angles to construct the dataset. Second, to ensure data diversity, the dataset covers a wide range of frame rates, resolutions, 419 classes of marine animals, and various static plants and terrains. Next, for task diversity, we adopted a structured design where observation targets are categorized into two major classes: biological and environmental. Each category includes content observation and change/action observation, totaling 20 subtask types. Finally, we designed several challenging evaluation metrics to enable quantitative comparison and analysis of different methods. Experiments on two representative VidLMs demonstrate that fine-tuning VidLMs on UVLM significantly improves underwater world understanding while also showing potential for slight improvements on existing in-air VidLM benchmarks.

Zitieren

APA

Xue, X., Zhou, Y., Yan, D., Tao, L., Li, J., Li, Y., Zhang, H., & Xiao, R. (2026). UVLM: Benchmarking Video Language Model for Underwater World Understanding. Proceedings of the AAAI Conference on Artificial Intelligence, 40(14), 11532-11540. https://doi.org/10.1609/aaai.v40i14.38136

Vancouver

Xue X, Zhou Y, Yan D, Tao L, Li J, Li Y, et al. UVLM: Benchmarking Video Language Model for Underwater World Understanding. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(14):11532-11540. doi:10.1609/aaai.v40i14.38136

BibTeX
@article{Xue2026,
  author = {Xue, Xizhe and Zhou, Yang and Yan, Dawei and Tao, Lijie and Li, Junjie and Li, Ying and Zhang, Haokui and Xiao, Rong},
  title = {UVLM: Benchmarking Video Language Model for Underwater World Understanding},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {14},
  pages = {11532--11540},
  doi = {10.1609/aaai.v40i14.38136}
}
Kostenlos starten →