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

Continuous computer vision (CV) tasks increasingly rely on convolutionalneural networks (CNN). However, CNNs have massive compute demands that farexceed the performance and energy constraints of mobile devices. In this paper,we propose and develop an algorithm-architecture co-designed system, Euphrates,that simultaneously improves the energy-efficiency and performance ofcontinuous vision tasks.  Our key observation is that changes in pixel data between consecutive framesrepresents visual motion. We first propose an algorithm that leverages thismotion information to relax the number of expensive CNN inferences required bycontinuous vision applications. We co-design a mobile System-on-a-Chip (SoC)architecture to maximize the efficiency of the new algorithm. The key to ourarchitectural augmentation is to co-optimize different SoC IP blocks in thevision pipeline collectively. Specifically, we propose to expose the motiondata that is naturally generated by the Image Signal Processor (ISP) early inthe vision pipeline to the CNN engine. Measurement and synthesis results showthat Euphrates achieves up to 66% SoC-level energy savings (4 times for thevision computations), with only 1% accuracy loss.

Euphrates: Algorithm-SoC Co-Design for Low-Power Mobile Continuous Vision