Retrieving events from large-scale video datasets is challenging due to complex temporal, spatial, and multimodal information. This paper presents U-CESE, our solution for the AI Challenge HCMC 2025, a Unified Clip-based Event Search Engine for multimodal event retrieval across diverse video sources. Building on CESE, U-CESE integrates its three modules into a single cohesive framework, ensuring consistent processing and retrieval across query types. A core component is the Unified Clipping Algorithm, which merges separate clipping algorithms into one efficient pipeline. To handle large-scale data, we propose DAKE, a lightweight, training-free keyframe extraction method using JPEG file size variations to identify significant scene changes. Finally, we introduce ReCap, a temporally consistent captioning framework inspired by Recurrent Neural Network, generating detailed and context-aware textual descriptions. Experiments show that U-CESE delivers robust, consistent, and efficient performance in large-scale multimodal event retrieval.
@article{arxiv.2605.23274,
title = {U-CESE: Unified Clip-based Event Search Engine for AI Challenge HCMC 2025},
author = {Duc-Nhuan Le and Hoang-Phuc Nguyen and Thanh-Duy Lam and Minh-Nhut Dang and Minh-Hoang Le},
journal= {arXiv preprint arXiv:2605.23274},
year = {2026}
}
Comments
Accepted for publication in the Proceedings of the 14th International Symposium on Information and Communication Technology (SOICT 2025)