Though pre-training vision-language models have demonstrated significant benefits in boosting video-text retrieval performance from large-scale web videos, fine-tuning still plays a critical role with manually annotated clips with start and end times, which requires considerable human effort. To address this issue, we explore an alternative cheaper source of annotations, single timestamps, for video-text retrieval. We initialise clips from timestamps in a heuristic way to warm up a retrieval model. Then a video clip editing method is proposed to refine the initial rough boundaries to improve retrieval performance. A student-teacher network is introduced for video clip editing. The teacher model is employed to edit the clips in the training set whereas the student model trains on the edited clips. The teacher weights are updated from the student's after the student's performance increases. Our method is model agnostic and applicable to any retrieval models. We conduct experiments based on three state-of-the-art retrieval models, COOT, VideoCLIP and CLIP4Clip. Experiments conducted on three video retrieval datasets, YouCook2, DiDeMo and ActivityNet-Captions show that our edited clips consistently improve retrieval performance over initial clips across all the three retrieval models.

翻译：尽管在大规模网络视频上预训练的视觉-语言模型已显著提升视频-文本检索性能，但微调过程仍依赖人工标注的包含起止时间的视频片段，这一环节需要大量人力投入。为解决该问题，本文探索了一种成本更低的替代标注方案——单时间戳标注——用于视频-文本检索任务。我们通过启发式方法从时间戳中初始化候选视频片段以预热检索模型，随后提出视频片段编辑方法对初始粗糙边界进行精细化调整以提升检索性能。我们引入师生网络架构进行视频片段编辑：教师模型用于修正训练集中的片段边界，学生模型则在修正后的片段上进行训练；当学生模型性能提升后，教师模型的权重将从学生模型同步更新。该方法具有模型无关性，可适用于任意检索模型。我们基于三种先进检索模型（COOT、VideoCLIP和CLIP4Clip）开展实验，并在YouCook2、DiDeMo和ActivityNet-Captions三个视频检索数据集上验证：相较于初始片段，经我们编辑的片段在所有三种检索模型上均能持续提升检索性能。