Video sentence grounding with temporally global textual knowledge

arXiv:2404.13611v1 Announce Type: new
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, …

abstract arxiv cs.cl cs.cv domain features gap global knowledge language moment natural natural language natural language query paper query retrieval temporal textual type video