Video grounding aims to localize a moment from an untrimmed video for a given textual query. Existing approaches focus more on the alignment of visual and language stimuli with various likelihood-based matching or regression strategies, i.e., P(Y|X). Consequently, these models may suffer from spurious correlations between the language and video features due to the selection bias of the dataset. 1) To uncover the causality behind the model and data, we first propose a novel paradigm from the perspective of the causal inference, i.e., interventional video grounding (IVG) that leverages backdoor adjustment to deconfound the selection bias based on structured causal model (SCM) and do-calculus P(Y|do(X)). Then, we present a simple yet effective method to approximate the unobserved confounder as it cannot be directly sampled from the dataset. 2) Meanwhile, we introduce a dual contrastive learning approach (DCL) to better align the text and video by maximizing the mutual information (MI) between query and video clips, and the MI between start/end frames of a target moment and the others within a video to learn more informative visual representations. Experiments on three standard benchmarks show the effectiveness of our approaches.

翻译：现有方法更侧重于使视觉和语言刺激与各种基于可能性的匹配或回归策略(即P(Y ⁇ X))相匹配。因此,这些模型可能由于数据集的选择偏差而使语言和视频特征之间出现虚假的关联。 1)为了发现模型和数据背后的因果关系,我们首先从因果推断的角度提出一个新的范例,即干预性视频定位(IVG),利用后门调整来打破基于结构化因果模型(SCM)和 do-calulus P(Y ⁇ do(X))的选择偏差。 然后,我们提出了一个简单而有效的方法,以近似未观察到的连接点,因为它无法直接从数据集中抽样。 2)同时,我们从因因因因因因果推断的角度出发,提出了双重对比学习方法(DCL),通过最大限度地利用查询和视频剪辑之间的相互信息来调整文本和视频,以及MI在开始/结束一个目标的图像基准框架之间,在开始/结束/结束一个图像基准以显示我们三个目标的图像基准中学习。