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

Spatio-temporal grounding describes the task of localizing events in spaceand time, e.g., in video data, based on verbal descriptions only. Models forthis task are usually trained with human-annotated sentences and bounding boxsupervision. This work addresses this task from a multimodal supervisionperspective, proposing a framework for spatio-temporal action grounding trainedon loose video and subtitle supervision only, without human annotation. To thisend, we combine local representation learning, which focuses on leveragingfine-grained spatial information, with a global representation encoding thatcaptures higher-level representations and incorporates both in a jointapproach. To evaluate this challenging task in a real-life setting, a newbenchmark dataset is proposed providing dense spatio-temporal groundingannotations in long, untrimmed, multi-action instructional videos for over 5Kevents. We evaluate the proposed approach and other methods on the proposed andstandard downstream tasks showing that our method improves over currentbaselines in various settings, including spatial, temporal, and untrimmedmulti-action spatio-temporal grounding.

What, when, and where? -- Self-Supervised Spatio-Temporal Grounding in Untrimmed Multi-Action Videos from Narrated Instructions