Leveraging Lightweight Entity Extraction for Scalable Event-Based Image Retrieval

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Minh, Dao Sy Duy, Kiet, Huynh Trung, Quy, Nguyen Lam Phu, Pham, Phu-Hoa, Nguyen, Tran Chi
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912788251672576
author Minh, Dao Sy Duy
Kiet, Huynh Trung
Quy, Nguyen Lam Phu
Pham, Phu-Hoa
Nguyen, Tran Chi
author_facet Minh, Dao Sy Duy
Kiet, Huynh Trung
Quy, Nguyen Lam Phu
Pham, Phu-Hoa
Nguyen, Tran Chi
contents Retrieving images from natural language descriptions is a core task at the intersection of computer vision and natural language processing, with wide-ranging applications in search engines, media archiving, and digital content management. However, real-world image-text retrieval remains challenging due to vague or context-dependent queries, linguistic variability, and the need for scalable solutions. In this work, we propose a lightweight two-stage retrieval pipeline that leverages event-centric entity extraction to incorporate temporal and contextual signals from real-world captions. The first stage performs efficient candidate filtering using BM25 based on salient entities, while the second stage applies BEiT-3 models to capture deep multimodal semantics and rerank the results. Evaluated on the OpenEvents v1 benchmark, our method achieves a mean average precision of 0.559, substantially outperforming prior baselines. These results highlight the effectiveness of combining event-guided filtering with long-text vision-language modeling for accurate and efficient retrieval in complex, real-world scenarios. Our code is available at https://github.com/PhamPhuHoa-23/Event-Based-Image-Retrieval
format Preprint
id arxiv_https___arxiv_org_abs_2512_21221
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Leveraging Lightweight Entity Extraction for Scalable Event-Based Image Retrieval
Minh, Dao Sy Duy
Kiet, Huynh Trung
Quy, Nguyen Lam Phu
Pham, Phu-Hoa
Nguyen, Tran Chi
Computer Vision and Pattern Recognition
Artificial Intelligence
I.2.10; H.3.3
Retrieving images from natural language descriptions is a core task at the intersection of computer vision and natural language processing, with wide-ranging applications in search engines, media archiving, and digital content management. However, real-world image-text retrieval remains challenging due to vague or context-dependent queries, linguistic variability, and the need for scalable solutions. In this work, we propose a lightweight two-stage retrieval pipeline that leverages event-centric entity extraction to incorporate temporal and contextual signals from real-world captions. The first stage performs efficient candidate filtering using BM25 based on salient entities, while the second stage applies BEiT-3 models to capture deep multimodal semantics and rerank the results. Evaluated on the OpenEvents v1 benchmark, our method achieves a mean average precision of 0.559, substantially outperforming prior baselines. These results highlight the effectiveness of combining event-guided filtering with long-text vision-language modeling for accurate and efficient retrieval in complex, real-world scenarios. Our code is available at https://github.com/PhamPhuHoa-23/Event-Based-Image-Retrieval
title Leveraging Lightweight Entity Extraction for Scalable Event-Based Image Retrieval
topic Computer Vision and Pattern Recognition
Artificial Intelligence
I.2.10; H.3.3
url https://arxiv.org/abs/2512.21221