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

Concept-based video representation has proven to be effective in complexevent detection. However, existing methods either manually design concepts ordirectly adopt concept libraries not specifically designed for events. In thispaper, we propose to build Concept Bank, the largest concept library consistingof 4,876 concepts specifically designed to cover 631 real-world events. Toconstruct the Concept Bank, we first gather a comprehensive event collectionfrom WikiHow, a collaborative writing project that aims to build the world'slargest manual for any possible How-To event. For each event, we then searchFlickr and discover relevant concepts from the tags of the returned images. Wetrain a Multiple Kernel Linear SVM for each discovered concept as a conceptdetector in Concept Bank. We organize the concepts into a five-layer treestructure, in which the higher-level nodes correspond to the event categorieswhile the leaf nodes are the event-specific concepts discovered for each event.Based on such tree ontology, we develop a semantic matching method to selectrelevant concepts for each textual event query, and then apply thecorresponding concept detectors to generate concept-based videorepresentations. We use TRECVID Multimedia Event Detection 2013 and ColumbiaConsumer Video open source event definitions and videos as our test sets andshow very promising results on two video event detection tasks: event modelingover concept space and zero-shot event retrieval. To the best of our knowledge,this is the largest concept library covering the largest number of real-worldevents.

Building A Large Concept Bank for Representing Events in Video