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 Tools annual

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 monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Visual Place Recognition (VPR) is the task of matching current visual imageryfrom a camera to images stored in a reference map of the environment. Whileinitial VPR systems used simple direct image methods or hand-crafted visualfeatures, recent work has focused on learning more powerful visual features andfurther improving performance through either some form of sequential matcher /filter or a hierarchical matching process. In both cases the performance of theinitial single-image based system is still far from perfect, puttingsignificant pressure on the sequence matching or (in the case of hierarchicalsystems) pose refinement stages. In this paper we present a novel hybrid systemthat creates a high performance initial match hypothesis generator using shortlearnt sequential descriptors, which enable selective control sequential scoreaggregation using single image learnt descriptors. Sequential descriptors aregenerated using a temporal convolutional network dubbed SeqNet, encoding shortimage sequences using 1-D convolutions, which are then matched against thecorresponding temporal descriptors from the reference dataset to provide anordered list of place match hypotheses. We then perform selective sequentialscore aggregation using shortlisted single image learnt descriptors from aseparate pipeline to produce an overall place match hypothesis. Comprehensiveexperiments on challenging benchmark datasets demonstrate the proposed methodoutperforming recent state-of-the-art methods using the same amount ofsequential information. Source code and supplementary material can be found athttps://github.com/oravus/seqNet.

SeqNet: Learning Descriptors for Sequence-based Hierarchical Place Recognition