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

Detecting suspicious activities in surveillance videos is a longstandingproblem in real-time surveillance that leads to difficulties in detectingcrimes. Hence, we propose a novel approach for detecting and summarizingsuspicious activities in surveillance videos. We have also created ground truthsummaries for the UCF-Crime video dataset. We modify a pre-existing approachfor this task by leveraging the Human-Object Interaction (HOI) model for theVisual features in the Bi-Modal Transformer. Further, we validate our approachagainst the existing state-of-the-art algorithms for the Dense Video Captioningtask for the ActivityNet Captions dataset. We observe that this formulation forDense Captioning performs significantly better than other discussed BMT-basedapproaches for BLEU@1, BLEU@2, BLEU@3, BLEU@4, and METEOR. We further perform acomparative analysis of the dataset and the model to report the findings basedon different NMS thresholds (searched using Genetic Algorithms). Here, ourformulation outperforms all the models for BLEU@1, BLEU@2, BLEU@3, and mostmodels for BLEU@4 and METEOR falling short of only ADV-INF Global by 25% and0.5%, respectively.

SAVCHOI: Detecting Suspicious Activities using Dense Video Captioning with Human Object Interactions