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

Many real-world video analysis applications require the ability to identifydomain-specific events in video, such as interviews and commercials in TV newsbroadcasts, or action sequences in film. Unfortunately, pre-trained models todetect all the events of interest in video may not exist, and training newmodels from scratch can be costly and labor-intensive. In this paper, weexplore the utility of specifying new events in video in a more traditionalmanner: by writing queries that compose outputs of existing, pre-trainedmodels. To write these queries, we have developed Rekall, a library thatexposes a data model and programming model for compositional video eventspecification. Rekall represents video annotations from different sources(object detectors, transcripts, etc.) as spatiotemporal labels associated withcontinuous volumes of spacetime in a video, and provides operators forcomposing labels into queries that model new video events. We demonstrate theuse of Rekall in analyzing video from cable TV news broadcasts, films,static-camera vehicular video streams, and commercial autonomous vehicle logs.In these efforts, domain experts were able to quickly (in a few hours to a day)author queries that enabled the accurate detection of new events (on par with,and in some cases much more accurate than, learned approaches) and to rapidlyretrieve video clips for human-in-the-loop tasks such as video content curationand training data curation. Finally, in a user study, novice users of Rekallwere able to author queries to retrieve new events in video given just one hourof query development time.

Rekall: Specifying Video Events using Compositions of Spatiotemporal Labels