不真实时刻：视频时刻检索中负查询的处理
Moment of Untruth: Dealing with Negative Queries in Video Moment Retrieval
AI总结：
针对视频时刻检索中无关查询导致假阳性预测的问题，提出负感知视频时刻检索任务，区分域内外负查询并构建新基准，提出UniVTG-NA模型，在实现98.4%平均负拒绝准确率的同时，Recall@1得分仅下降3.87%。
摘要：
视频时刻检索是评估视觉语言模型性能的常见任务，需根据查询语句定位视频中时刻的开始和结束时间。当前任务设定假设查询时刻存在于视频中，导致提供无关查询语句时会出现假阳性时刻预测。本文提出负感知视频时刻检索（NA-VMR）任务，同时考虑时刻检索准确率和负查询拒绝准确率。我们区分域内和域外负查询，并为QVHighlights和Charades-STA两个热门视频时刻检索数据集提供新的评估基准。我们分析现有SOTA视频时刻检索方法适应负感知视频时刻检索的能力，并提出UniVTG-NA——一种专为解决NA-VMR而设计的UniVTG改编模型。UniVTG-NA实现了98.4%的平均负拒绝准确率，同时时刻检索Recall@1得分仅下降3.87%。数据集拆分和代码可在https://github.com/keflanagan/MomentofUntruth获取。
英文摘要：
Video Moment Retrieval is a common task to evaluate the performance of visual-language models - it involves localising start and end times of moments in videos from query sentences. The current task formulation assumes that the queried moment is present in the video, resulting in false positive moment predictions when irrelevant query sentences are provided. In this paper we propose the task of Negative-Aware Video Moment Retrieval (NA-VMR), which considers both moment retrieval accuracy and negative query rejection accuracy. We make the distinction between In-Domain and Out-of-Domain negative queries and provide new evaluation benchmarks for two popular video moment retrieval datasets: QVHighlights and Charades-STA. We analyse the ability of current SOTA video moment retrieval approaches to adapt to Negative-Aware Video Moment Retrieval and propose UniVTG-NA, an adaptation of UniVTG designed to tackle NA-VMR. UniVTG-NA achieves high negative rejection accuracy (avg. $98.4\%$) scores while retaining moment retrieval scores to within $3.87\%$ Recall@1. Dataset splits and code are available at https://github.com/keflanagan/MomentofUntruth
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
