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

As humans we possess an intuitive ability for navigation which we masterthrough years of practice; however existing approaches to model this trait fordiverse tasks including monitoring pedestrian flow and detecting abnormalevents have been limited by using a variety of hand-crafted features. Recentresearch in the area of deep-learning has demonstrated the power of learningfeatures directly from the data; and related research in recurrent neuralnetworks has shown exemplary results in sequence-to-sequence problems such asneural machine translation and neural image caption generation. Motivated bythese approaches, we propose a novel method to predict the future motion of apedestrian given a short history of their, and their neighbours, pastbehaviour. The novelty of the proposed method is the combined attention modelwhich utilises both "soft attention" as well as "hard-wired" attention in orderto map the trajectory information from the local neighbourhood to the futurepositions of the pedestrian of interest. We illustrate how a simpleapproximation of attention weights (i.e hard-wired) can be merged together withsoft attention weights in order to make our model applicable for challengingreal world scenarios with hundreds of neighbours. The navigational capabilityof the proposed method is tested on two challenging publicly availablesurveillance databases where our model outperforms the current-state-of-the-artmethods. Additionally, we illustrate how the proposed architecture can bedirectly applied for the task of abnormal event detection without handcraftingthe features.

Soft + Hardwired Attention: An LSTM Framework for Human Trajectory Prediction and Abnormal Event Detection