Local-Global Video-Text Interactions for Temporal Grounding
CVPR, pp. 10807-10816, 2020.
We have presented a novel local-global video-text interaction algorithm for text-to-video temporal grounding via constituent semantic phrase extraction
This paper addresses the problem of text-to-video temporal grounding, which aims to identify the time interval in a video semantically relevant to a text query. We tackle this problem using a novel regression-based model that learns to extract a collection of mid-level features for semantic phrases in a text query, which corresponds to ...More
PPT (Upload PPT)