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

Visual Place Recognition (VPR) is a crucial component of 6-DoF localization,visual SLAM and structure-from-motion pipelines, tasked to generate an initiallist of place match hypotheses by matching global place descriptors. However,commonly-used CNN-based methods either process multiple image resolutions aftertraining or use a single resolution and limit multi-scale feature extraction tothe last convolutional layer during training. In this paper, we augment NetVLADrepresentation learning with low-resolution image pyramid encoding which leadsto richer place representations. The resultant multi-resolution feature pyramidcan be conveniently aggregated through VLAD into a single compactrepresentation, avoiding the need for concatenation or summation of multiplepatches in recent multi-scale approaches. Furthermore, we show that theunderlying learnt feature tensor can be combined with existing multi-scaleapproaches to improve their baseline performance. Evaluation on 15viewpoint-varying and viewpoint-consistent benchmarking datasets confirm thatthe proposed MultiRes-NetVLAD leads to state-of-the-art Recall@N performancefor global descriptor based retrieval, compared against 11 existing techniques.Source code is publicly available athttps://github.com/Ahmedest61/MultiRes-NetVLAD.

MultiRes-NetVLAD: Augmenting Place Recognition Training With Low-Resolution Imagery