Abstract
Video moment localization, also known as video moment retrieval, aiming to search a target segment within a video described by a given natural language query. Beyond the task of temporal action localization whereby the target actions are pre-defined, video moment retrieval can query arbitrary complex activities. In this survey paper, we aim to present a comprehensive review of existing video moment localization techniques, including supervised, weakly supervised, and unsupervised ones. We also review the datasets available for video moment localization and group results of related work. In addition, we discuss promising future directions for this field, in particular large-scale datasets and interpretable video moment localization models.
Abstract (translated)
视频时刻定位(Video moment localization，又称视频时刻检索)旨在根据给定自然语言查询搜索视频中指定目标片段。除了时间行为定位任务(target actions are pre-defined in this task)，视频时刻检索还可以查询任意复杂的活动。在这份调查 paper 中，我们旨在全面综述现有的视频时刻定位技术，包括受监督、弱监督和无监督的。我们还 review 了用于视频时刻定位的可用数据集和相关工作的群体结果。此外，我们讨论了该领域有前景的未来方向，特别是大规模数据集和可解释的视频时刻定位模型。
URL
https://arxiv.org/abs/2306.07515
