Moment retrieval aims to locate the most relevant moment in an untrimmed video based on a given natural language query. Existing solutions can be roughly categorized into moment-based and clip-based methods. The former often involves heavy computations, while the latter, due to overlooking coarse-grained information, typically underperforms compared to moment-based models. Hence, this paper proposes a novel 2-Dimensional Pointer-based Machine Reading Comprehension for Moment Retrieval Choice (2DP-2MRC) model to address the issue of imprecise localization in clip-based methods while maintaining lower computational complexity than moment-based methods. Specifically, we introduce an AV-Encoder to capture coarse-grained information at moment and video levels. Additionally, a 2D pointer encoder module is introduced to further enhance boundary detection for target moment. Extensive experiments on the HiREST dataset demonstrate that 2DP-2MRC significantly outperforms existing baseline models.
@article{arxiv.2406.06201,
title = {2DP-2MRC: 2-Dimensional Pointer-based Machine Reading Comprehension Method for Multimodal Moment Retrieval},
author = {Jiajun He and Tomoki Toda},
journal= {arXiv preprint arXiv:2406.06201},
year = {2024}
}