Journal article · 2026 · Open access

AquaticCLIP: A Vision-Language Foundation Model and Dataset for Underwater Scene Analysis

Basit Alawode, Iyyakutti Iyappan Ganapathi, Sajid Javed, Mohammed Bennamoun, Arif Mahmood

IEEE Transactions on Neural Networks and Learning Systems, 37(8), 3956–3969 · Published 9 February 2026 · DOI 10.1109/tnnls.2026.3657138

Open full textCite this paper

In brief

“AquaticCLIP: A Vision-Language Foundation Model and Dataset for Underwater Scene Analysis” is a 2026 journal article by Basit Alawode and 4 co-authors, published in IEEE Transactions on Neural Networks and Learning Systems. OpenAlex counts 23 citations as of 17 November 2026, which puts it in the top 5% of works published in 2026 by citations. It is open access under a CC BY-NC-ND licence: the full text is free to read at IEEE Transactions on Neural Networks and Learning Systems.

Citations
23
Most cited in
2026 (17)
Field-weighted impact
23.50
References
125
Authors
5

Abstract

The preservation of aquatic biodiversity is critical in mitigating the effects of climate change. Aquatic scene understanding plays a pivotal role in aiding marine scientists in their decision-making processes. In this article, we introduce AquaticCLIP, a novel contrastive language-image pretraining (CLIP) model tailored for aquatic scene understanding. AquaticCLIP presents an underwater domain-specific learning framework that aligns images and texts in aquatic environments, enabling tasks such as segmentation, classification, detection, and object counting. By leveraging our large-scale underwater image-text paired dataset without the need for ground-truth (GT) annotations, our model enriches existing vision-language models (VLMs) in the aquatic domain. For this purpose, we construct a 2-million underwater image-text paired dataset using heterogeneous resources, including YouTube, Netflix, National Geographic (NatGeo), etc. To fine-tune AquaticCLIP, we propose a prompt-guided vision encoder (PGVE) that progressively aggregates patch features via learnable prompts, while a vision-guided mechanism enhances the language encoder by incorporating visual context. The model is optimized through a contrastive pretraining loss to align visual and textual modalities. AquaticCLIP achieves notable performance improvements in zero-shot settings across multiple underwater computer vision tasks, outperforming existing methods in both accuracy and robustness. Our model sets a new benchmark for vision-language applications in underwater environments. The code and dataset for AquaticCLIP are publicly available on GitHub at: https://github.com/BasitAlawode/AquaticCLIP.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Alawode, B., Ganapathi, I. I., Javed, S., Bennamoun, M., & Mahmood, A. (2026). AquaticCLIP: A Vision-Language Foundation Model and Dataset for Underwater Scene Analysis. IEEE Transactions on Neural Networks and Learning Systems, 37(8), 3956–3969. https://doi.org/10.1109/tnnls.2026.3657138

MLA 9

Alawode, Basit, et al. “AquaticCLIP: A Vision-Language Foundation Model and Dataset for Underwater Scene Analysis.” IEEE Transactions on Neural Networks and Learning Systems, vol. 37, no. 8, 2026, pp. 3956–3969. https://doi.org/10.1109/tnnls.2026.3657138.

Chicago

Alawode, Basit, Iyyakutti Iyappan Ganapathi, Sajid Javed, Mohammed Bennamoun, and Arif Mahmood. 2026. “AquaticCLIP: A Vision-Language Foundation Model and Dataset for Underwater Scene Analysis.” IEEE Transactions on Neural Networks and Learning Systems 37 (8): 3956–3969. https://doi.org/10.1109/tnnls.2026.3657138.

Harvard

Alawode, B. et al. (2026) ‘AquaticCLIP: A Vision-Language Foundation Model and Dataset for Underwater Scene Analysis’, IEEE Transactions on Neural Networks and Learning Systems, 37(8), pp. 3956–3969. doi:10.1109/tnnls.2026.3657138.

IEEE

B. Alawode, I. I. Ganapathi, S. Javed, M. Bennamoun, and A. Mahmood, “AquaticCLIP: A Vision-Language Foundation Model and Dataset for Underwater Scene Analysis,” IEEE Transactions on Neural Networks and Learning Systems, vol. 37, no. 8, pp. 3956–3969, 2026, doi: 10.1109/tnnls.2026.3657138.

BibTeX

@article{alawode2026aquaticclip,
  title     = {{AquaticCLIP: A Vision-Language Foundation Model and Dataset for Underwater Scene Analysis}},
  author    = {Alawode, Basit and Ganapathi, Iyyakutti Iyappan and Javed, Sajid and Bennamoun, Mohammed and Mahmood, Arif},
  journal   = {IEEE Transactions on Neural Networks and Learning Systems},
  year      = {2026},
  volume    = {37},
  number    = {8},
  pages     = {3956--3969},
  doi       = {10.1109/tnnls.2026.3657138},
  url       = {https://doi.org/10.1109/tnnls.2026.3657138}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Topic and keywords

Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Multimodal Machine Learning Applications

  • vision-language models
  • contrastive language-image pretraining
  • underwater object detection
  • aquatic biodiversity

Work with this paper

Most-cited papers in Computer Science

All highly cited Computer Science papers

Questions about this paper

How do I cite this paper in APA style?

Alawode, B., Ganapathi, I. I., Javed, S., Bennamoun, M., & Mahmood, A. (2026). AquaticCLIP: A Vision-Language Foundation Model and Dataset for Underwater Scene Analysis. IEEE Transactions on Neural Networks and Learning Systems, 37(8), 3956–3969. https://doi.org/10.1109/tnnls.2026.3657138

How many times has this paper been cited?

23 times, according to OpenAlex on 17 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

Yes. It is open access at IEEE Transactions on Neural Networks and Learning Systems: sign in and open the full text from this page.

Who wrote this paper?

Basit Alawode, Iyyakutti Iyappan Ganapathi, Sajid Javed, Mohammed Bennamoun, Arif Mahmood.

What is the DOI of this paper?

10.1109/tnnls.2026.3657138, permanently at https://doi.org/10.1109/tnnls.2026.3657138. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 17 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.