English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Natural language spatial video grounding aims to detect the relevant objectsin video frames with descriptive sentences as the query. In spite of the greatadvances, most existing methods rely on dense video frame annotations, whichrequire a tremendous amount of human effort. To achieve effective groundingunder a limited annotation budget, we investigate one-shot video grounding, andlearn to ground natural language in all video frames with solely one framelabeled, in an end-to-end manner. One major challenge of end-to-end one-shotvideo grounding is the existence of videos frames that are either irrelevant tothe language query or the labeled frames. Another challenge relates to thelimited supervision, which might result in ineffective representation learning.To address these challenges, we designed an end-to-end model via InformationTree for One-Shot video grounding (IT-OS). Its key module, the informationtree, can eliminate the interference of irrelevant frames based on branchsearch and branch cropping techniques. In addition, several self-supervisedtasks are proposed based on the information tree to improve the representationlearning under insufficient labeling. Experiments on the benchmark datasetdemonstrate the effectiveness of our model.

End-to-End Modeling via Information Tree for One-Shot Natural Language Spatial Video Grounding