Abstract
Almost all previous text-to-video retrieval works ideally assume that videos are pre-trimmed with short durations containing solely text-related content. However, in practice, videos are typically untrimmed in long durations with much more complicated background content. Therefore, in this paper, we focus on the more practical yet challenging task of Partially Relevant Video Retrieval (PRVR), which aims to retrieve partially relevant untrimmed videos with the given query. To tackle this task, we propose a novel framework that distills generalization knowledge from a powerful large-scale vision-language pre-trained model and transfers it to a lightweight, task-specific PRVR network. Specifically, we introduce a Dual Learning framework with Dynamic Knowledge Distillation (DL-DKD++), where a large teacher model provides supervision to a compact dual-branch student network. The student model comprises two branches: an inheritance branch that absorbs transferable knowledge from the teacher, and an exploration branch that learns task-specific information from the PRVR dataset to address domain gaps. To further enhance learning, we incorporate a dynamic soft-target construction mechanism. By replacing rigid hard-target supervision with adaptive soft targets that evolve during training, our method enables the model to better capture the fine-grained, partial relevance between videos and queries. Experiment results demonstrate that our proposed model achieves state-of-the-art performance on TVR, ActivityNet, and Charades-STA datasets for PRVR. The code is available at this https URL.
Abstract (translated)
几乎所有的之前用于文本到视频检索的工作都假定视频已经被裁剪为含有纯文本相关内容的短片段。然而，在实际应用中，视频通常是以长时间段的形式存在，并且包含复杂的背景内容。因此，在本文中，我们专注于更为实用但更具挑战性的任务——部分相关视频检索（PRVR），该任务旨在根据给定查询检索出部分相关的未裁剪视频。为了应对这一任务，我们提出了一种新颖的框架，从一个强大的大规模视觉-语言预训练模型中提炼泛化知识，并将其转移至轻量级的任务特定PRVR网络上。 具体而言，我们引入了带有动态知识蒸馏（DL-DKD++）的双学习框架，在该框架下，大型教师模型为紧凑的双支路学生网络提供了监督。学生模型包含两个分支：一个继承分支从教师那里吸收可转移的知识，另一个探索分支则从PRVR数据集中学习任务特定的信息来解决领域差距问题。 为了进一步增强学习效果，我们引入了动态软目标构建机制。通过用在训练过程中不断演化的自适应软标签替代刚性的硬标签监督，我们的方法使模型能够更好地捕捉视频和查询之间的细微部分相关性。 实验结果表明，在TVR、ActivityNet 和 Charades-STA 数据集上进行的 PRVR 任务中，我们提出的模型达到了最先进的性能。代码可在此网址获取：[https URL]。
URL
https://arxiv.org/abs/2510.12283
