Cross-Lingual Cross-Modal Consolidation for Effective Multilingual Video Corpus Moment Retrieval

Abstract

Existing multilingual video corpus moment retrieval (mVCMR) methods are mainly based on a two-stream structure. The visual stream utilizes the visual content in the video to estimate the query-visual similarity, and the subtitle stream exploits the query-subtitle similarity. The final query-video similarity ensembles similarities from two streams. In our work, we propose a simple and effective strategy termed as Cross-lingual Cross-modal Consolidation (C3) to improve mVCMR accuracy. We adopt the ensemble similarity as the teacher to guide the training of each stream, leading to a more powerful ensemble similarity. Meanwhile, we use the teacher for a specific language to guide the student for another language to exploit the complementary knowledge across languages. Extensive experiments on mTVR dataset demonstrate the effectiveness of our C3 method.