{"ID":2889512,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.20564","arxiv_id":"2507.20564","title":"ZSE-Cap: A Zero-Shot Ensemble for Image Retrieval and Prompt-Guided Captioning","abstract":"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.","short_abstract":"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,...","url_abs":"https://arxiv.org/abs/2507.20564","url_pdf":"https://arxiv.org/pdf/2507.20564v1","authors":"[\"Duc-Tai Dinh\",\"Duc Anh Khoa Dinh\"]","published":"2025-07-28T06:58:35Z","proceeding":"cs.CL","tasks":"[\"cs.CL\",\"cs.IR\"]","methods":"[]","has_code":false,"code_links":[{"ID":611653,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2889512,"paper_url":"https://arxiv.org/abs/2507.20564","paper_title":"ZSE-Cap: A Zero-Shot Ensemble for Image Retrieval and Prompt-Guided Captioning","repo_url":"https://github.com/ductai05/ZSE-Cap","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}