This study focuses on weakly-supervised Video Moment Retrieval (VMR), aiming to identify a moment semantically similar to the given query within an untrimmed video using only video-level correspondences, without relying on temporal annotations during training. Previous methods either aggregate predictions for all instances in the video, or indirectly address the task by proposing reconstructions for the query. However, these methods often produce low-quality temporal proposals, struggle with distinguishing misaligned moments in the same video, or lack stability due to a reliance on a single auxiliary task. To address these limitations, we present a novel weakly-supervised method called Multi-proposal Collaboration and Multi-task Training (MCMT). Initially, we generate multiple proposals and derive corresponding learnable Gaussian masks from them. These masks are then combined to create a high-quality positive sample mask, highlighting video clips most relevant to the query. Concurrently, we classify other clips in the same video as the easy negative sample and the entire video as the hard negative sample. During training, we introduce forward and inverse masked query reconstruction tasks to impose more substantial constraints on the network, promoting more robust and stable retrieval performance. Extensive experiments on two standard benchmarks affirm the effectiveness of the proposed method in VMR.

翻译：本研究聚焦于弱监督视频时刻检索（Video Moment Retrieval, VMR），旨在仅利用视频级标注对应关系，在无需训练时时间标注的情况下，从未修剪的视频中定位与给定查询语义相似的视频片段。现有方法要么汇总视频中所有实例的预测结果，要么通过为查询提出重建任务来间接处理该问题。然而，这些方法常生成质量较低的时间提案，难以区分同一视频中语义错位的时刻，或因依赖单一辅助任务而缺乏稳定性。为解决上述局限，我们提出一种名为多提案协作与多任务训练（Multi-proposal Collaboration and Multi-task Training, MCMT）的新型弱监督方法。首先，我们生成多个提案并从中推导出相应的可学习高斯掩码。随后，将这些掩码融合以构建一个高质量的正样本掩码，突出与查询最相关的视频片段。同时，将同一视频中的其他片段归类为简单负样本，并将整个视频视为困难负样本。在训练过程中，引入前向和逆向掩码查询重建任务，对网络施加更强的约束，从而促进更稳健且稳定的检索性能。在两个标准基准上的大量实验验证了所提方法在VMR中的有效性。