Video sentence grounding with temporally global textual knowledge

TL;DR

This paper introduces a novel approach for temporal sentence grounding in videos by leveraging pseudo-query features with global textual knowledge to improve multi-modal feature alignment and grounding accuracy.

Contribution

We propose the Pseudo-query Intermediary Network (PIN) that uses contrastive learning and learnable prompts to better align visual and textual features for temporal grounding.

Findings

Significant improvement on Charades-STA dataset

Effective bridging of domain gap between modalities

Enhanced feature alignment with pseudo-query knowledge

Abstract

Temporal sentence grounding involves the retrieval of a video moment with a natural language query. Many existing works directly incorporate the given video and temporally localized query for temporal grounding, overlooking the inherent domain gap between different modalities. In this paper, we utilize pseudo-query features containing extensive temporally global textual knowledge sourced from the same video-query pair, to enhance the bridging of domain gaps and attain a heightened level of similarity between multi-modal features. Specifically, we propose a Pseudo-query Intermediary Network (PIN) to achieve an improved alignment of visual and comprehensive pseudo-query features within the feature space through contrastive learning. Subsequently, we utilize learnable prompts to encapsulate the knowledge of pseudo-queries, propagating them into the textual encoder and multi-modal fusion module, further enhancing the feature alignment between visual and language for better temporal grounding. Extensive experiments conducted on the Charades-STA and ActivityNet-Captions datasets demonstrate the effectiveness of our method.