Score: 1

ZSE-Cap: A Zero-Shot Ensemble for Image Retrieval and Prompt-Guided Captioning

Published: July 28, 2025 | arXiv ID: 2507.20564v1

By: Duc-Tai Dinh, Duc Anh Khoa Dinh

Potential Business Impact:

Helps computers describe pictures using article words.

Business Areas:
Image Recognition Data and Analytics, Software

We present ZSE-Cap (Zero-Shot Ensemble for Captioning), our 4th place system in Event-Enriched Image Analysis (EVENTA) shared task on article-grounded image retrieval and captioning. Our zero-shot approach requires no finetuning on the competition's data. For retrieval, we ensemble similarity scores from CLIP, SigLIP, and DINOv2. For captioning, we leverage a carefully engineered prompt to guide the Gemma 3 model, enabling it to link high-level events from the article to the visual content in the image. Our system achieved a final score of 0.42002, securing a top-4 position on the private test set, demonstrating the effectiveness of combining foundation models through ensembling and prompting. Our code is available at https://github.com/ductai05/ZSE-Cap.

Repos / Data Links

Page Count
7 pages

Category
Computer Science:
Computation and Language