Work

NU_Internship team at ImageEval 2025: From Zero-Shot to Ensembles: Enhancing Grounded Arabic Image Captioning

Year: 2025

Type: conference-paper

Abstract: Arabic image captioning remains underexplored in vision-language research due to limited resources and the linguistic complexity of Arabic.In the ImageEval 2025 Shared Task, we evaluated three models, AIN, BLIP-Arabic-Flickr-8k, and Qwen 2.5, across zero-shot, fine-tuning, retrieval-augmented, and ensemble setups.Our official submission, fine-tuned BLIP with retrieval augmentation, ranked 5th overall based on both cosine similarity and LLM-as-a-judge scores.Post-submission experiments showed that ensemble captioning yielded the strongest captions across metrics.These findings demonstrate that even modest fine-tuning combined with retrieval augmentation can substantially improve Arabic captioning quality, which is significant in light of the limited resources for the language.

Source: Arabic Natural Language Processing Workshop (WANLP)

DOI: 10.18653/v1/2025.arabicnlp-sharedtasks.58

Authors: Rana Gaber, Seif Eldin Amgad, Ahmed Sherif Nasri, Mohamed Ibrahim Ragab, Ensaf Hussein Mohamed

Institutions: Alexandria University, Ain Shams University, Nile University, Nile University

Language: English

Topic: Multimodal Machine Learning Applications

Subfield: Computer Vision and Pattern Recognition

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

OpenAlex ID: W4416037775

FWCI: 0.751

Cites:

Cited by: 1

Related to: 10