The exponential growth of digital video content has posed critical challenges in moment-level video retrieval, where existing methodologies struggle to efficiently localize specific segments within an expansive video corpus. Current retrieval systems are constrained by computational inefficiencies, temporal context limitations, and the intrinsic complexity of navigating video content. In this paper, we address these limitations through a novel Interactive Video Corpus Moment Retrieval framework that integrates a SuperGlobal Reranking mechanism and Adaptive Bidirectional Temporal Search (ABTS), strategically optimizing query similarity, temporal stability, and computational resources. By preprocessing a large corpus of videos using a keyframe extraction model and deduplication technique through image hashing, our approach provides a scalable solution that significantly reduces storage requirements while maintaining high localization precision across diverse video repositories.
View on arXiv@article{nguyen-nhu2025_2504.09298,
title={ A Lightweight Moment Retrieval System with Global Re-Ranking and Robust Adaptive Bidirectional Temporal Search },
author={ Tinh-Anh Nguyen-Nhu and Huu-Loc Tran and Nguyen-Khang Le and Minh-Nhat Nguyen and Tien-Huy Nguyen and Hoang-Long Nguyen-Huu and Huu-Phong Phan-Nguyen and Huy-Thach Pham and Quan Nguyen and Hoang M. Le and Quang-Vinh Dinh },
journal={arXiv preprint arXiv:2504.09298},
year={ 2025 }
}