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/

Zendy Plus

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

Zendy Tools

Zendy Open

Visual place recognition (VPR) in condition-varying environments is still anopen problem. Popular solutions are CNN-based image descriptors, which havebeen shown to outperform traditional image descriptors based on hand-craftedvisual features. However, there are two drawbacks of current CNN-baseddescriptors: a) their high dimension and b) lack of generalization, leading tolow efficiency and poor performance in applications. In this paper, we proposeto use a convolutional autoencoder (CAE) to tackle this problem. We employ ahigh-level layer of a pre-trained CNN to generate features, and train a CAE tomap the features to a low-dimensional space to improve the condition invarianceproperty of the descriptor and reduce its dimension at the same time. We verifyour method in three challenging datasets involving significant illuminationchanges, and our method is shown to be superior to the state-of-the-art. Forthe benefit of the community, we make public the source code.

Condition-Invariant and Compact Visual Place Description by Convolutional Autoencoder