Given a text query, partially relevant video retrieval (PRVR) seeks to find untrimmed videos containing pertinent moments in a database. For PRVR, clip modeling is essential to capture the partial relationship between texts and videos. Current PRVR methods adopt scanning-based clip construction to achieve explicit clip modeling, which is information-redundant and requires a large storage overhead. To solve the efficiency problem of PRVR methods, this paper proposes GMMFormer, a \textbf{G}aussian-\textbf{M}ixture-\textbf{M}odel based Trans\textbf{former} which models clip representations implicitly. During frame interactions, we incorporate Gaussian-Mixture-Model constraints to focus each frame on its adjacent frames instead of the whole video. Then generated representations will contain multi-scale clip information, achieving implicit clip modeling. In addition, PRVR methods ignore semantic differences between text queries relevant to the same video, leading to a sparse embedding space. We propose a query diverse loss to distinguish these text queries, making the embedding space more intensive and contain more semantic information. Extensive experiments on three large-scale video datasets (\ie, TVR, ActivityNet Captions, and Charades-STA) demonstrate the superiority and efficiency of GMMFormer.

翻译：给定一个文本查询，部分相关视频检索（PRVR）旨在从数据库中找出包含相关时刻的未修剪视频。对于PRVR，片段建模对于捕捉文本与视频之间的部分关系至关重要。现有PRVR方法采用扫描式片段构建来实现显式片段建模，这种方法存在信息冗余且需要大量存储开销。为解决PRVR方法的效率问题，本文提出GMMFormer——一种基于高斯混合模型（GMM）的Transformer，它隐式地对片段表示进行建模。在帧交互过程中，我们引入高斯混合模型约束，使每一帧聚焦于其相邻帧而非整个视频。由此生成的表示将包含多尺度片段信息，从而实现隐式片段建模。此外，PRVR方法忽略了与同一视频相关的文本查询之间的语义差异，导致嵌入空间稀疏。我们提出一种查询多样性损失来区分这些文本查询，使嵌入空间更加密集并包含更多语义信息。在三个大规模视频数据集（即TVR、ActivityNet Captions和Charades-STA）上的广泛实验证明了GMMFormer的优越性和高效性。