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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Practical video analytics systems that are deployed in bandwidth constrainedenvironments like autonomous vehicles perform computer vision tasks such asface detection and recognition. In an end-to-end face analytics system, inputsare first compressed using popular video codecs like HEVC and then passed ontomodules that perform face detection, alignment, and recognition sequentially.Typically, the modules of these systems are evaluated independently usingtask-specific imbalanced datasets that can misconstrue performance estimates.In this paper, we perform a thorough end-to-end evaluation of a face analyticssystem using a driving-specific dataset, which enables meaningfulinterpretations. We demonstrate how independent task evaluations, datasetimbalances, and inconsistent annotations can lead to incorrect systemperformance estimates. We propose strategies to create balanced evaluationsubsets of our dataset and to make its annotations consistent across multipleanalytics tasks and scenarios. We then evaluate the end-to-end systemperformance sequentially to account for task interdependencies. Our experimentsshow that our approach provides consistent, accurate, and interpretableestimates of the system's performance which is critical for real-worldapplications.

End-to-end Evaluation of Practical Video Analytics Systems for Face Detection and Recognition