Litcius/Paper detail

Deconfounded Video Moment Retrieval with Causal Intervention

Xun Yang, Fuli Feng, Wei Ji, Meng Wang, Tat‐Seng Chua

2021190 citationsDOIOpen Access PDF

Abstract

We tackle the task of video moment retrieval (VMR), which aims to localize a specific moment in a video according to a textual query. Existing methods primarily model the matching relationship between query and moment by complex cross-modal interactions. Despite their effectiveness, current models mostly exploit dataset biases while ignoring the video content, thus leading to poor generalizability. We argue that the issue is caused by the hidden confounder in VMR, i.e., temporal location of moments, that spuriously correlates the model input and prediction. How to design robust matching models against the temporal location biases is crucial but, as far as we know, has not been studied yet for VMR.

Topics & Concepts

Generalizability theoryComputer scienceMoment (physics)Matching (statistics)ExploitTask (project management)Artificial intelligenceStatisticsMathematicsEconomicsManagementClassical mechanicsComputer securityPhysicsMultimodal Machine Learning ApplicationsAdvanced Image and Video Retrieval TechniquesVideo Analysis and Summarization