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

Recent advances in visual activity recognition have raised the possibility ofapplications such as automated video surveillance. Effective approaches forsuch problems however require the ability to recognize the plans of agents fromvideo information. Although traditional plan recognition algorithms depend onaccess to sophisticated planning domain models, one recent promising directioninvolves learning approximated (or shallow) domain models directly from theobserved activity sequences DUP. One limitation is that such approaches expectobserved action sequences as inputs. In many cases involving vision/sensingfrom raw data, there is considerable uncertainty about the specific action atany given time point. The most we can expect in such cases is probabilisticinformation about the action at that point. The input will then be sequences ofsuch observed action distributions. In this work, we address the problem ofconstructing an effective data-interface that allows a plan recognition moduleto directly handle such observation distributions. Such an interface works likea bridge between the low-level perception module, and the high-level planrecognition module. We propose two approaches. The first involves resamplingthe distribution sequences to single action sequences, from which we couldlearn an action affinity model based on learned action (word) embeddings forplan recognition. The second is to directly learn action distributionembeddings by our proposed Distr2vec (distribution to vector) model, toconstruct an affinity model for plan recognition.

Recognizing Plans by Learning Embeddings from Observed Action Distributions