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

Video temporal grounding aims to pinpoint a video segment that matches thequery description. Despite the recent advance in short-form videos(\textit{e.g.}, in minutes), temporal grounding in long videos (\textit{e.g.},in hours) is still at its early stage. To address this challenge, a commonpractice is to employ a sliding window, yet can be inefficient and inflexibledue to the limited number of frames within the window. In this work, we proposean end-to-end framework for fast temporal grounding, which is able to model anhours-long video with \textbf{one-time} network execution. Our pipeline isformulated in a coarse-to-fine manner, where we first extract context knowledgefrom non-overlapped video clips (\textit{i.e.}, anchors), and then supplementthe anchors that highly response to the query with detailed content knowledge.Besides the remarkably high pipeline efficiency, another advantage of ourapproach is the capability of capturing long-range temporal correlation, thanksto modeling the entire video as a whole, and hence facilitates more accurategrounding. Experimental results suggest that, on the long-form video datasetsMAD and Ego4d, our method significantly outperforms state-of-the-arts, andachieves \textbf{14.6$\times$} / \textbf{102.8$\times$} higher efficiencyrespectively. Project can be found at\url{https://github.com/afcedf/SOONet.git}.

Scanning Only Once: An End-to-end Framework for Fast Temporal Grounding in Long Videos