|国家预印本平台
首页|ZSE-Cap: A Zero-Shot Ensemble for Image Retrieval and Prompt-Guided Captioning

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

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

来源:Arxiv_logoArxiv
英文摘要

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.

Duc-Tai Dinh、Duc Anh Khoa Dinh

计算技术、计算机技术

Duc-Tai Dinh,Duc Anh Khoa Dinh.ZSE-Cap: A Zero-Shot Ensemble for Image Retrieval and Prompt-Guided Captioning[EB/OL].(2025-07-28)[2025-08-18].https://arxiv.org/abs/2507.20564.点此复制

评论