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

In vision-enabled autonomous systems such as robots and autonomous cars,video object detection plays a crucial role, and both its speed and accuracyare important factors to provide reliable operation. The key insight we show inthis paper is that speed and accuracy are not necessarily a trade-off when itcomes to image scaling. Our results show that re-scaling the image to a lowerresolution will sometimes produce better accuracy. Based on this observation,we propose a novel approach, dubbed AdaScale, which adaptively selects theinput image scale that improves both accuracy and speed for video objectdetection. To this end, our results on ImageNet VID and miniYouTube-BoundingBoxes datasets demonstrate 1.3 points and 2.7 points mAPimprovement with 1.6x and 1.8x speedup, respectively. Additionally, we improvestate-of-the-art video acceleration work by an extra 1.25x speedup withslightly better mAP on ImageNet VID dataset.

AdaScale: Towards Real-time Video Object Detection Using Adaptive Scaling