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

Aerial scene recognition is a fundamental visual task and has attracted anincreasing research interest in the last few years. Most of current researchesmainly deploy efforts to categorize an aerial image into one scene-level label,while in real-world scenarios, there often exist multiple scenes in a singleimage. Therefore, in this paper, we propose to take a step forward to a morepractical and challenging task, namely multi-scene recognition in singleimages. Moreover, we note that manually yielding annotations for such a task isextraordinarily time- and labor-consuming. To address this, we propose aprototype-based memory network to recognize multiple scenes in a single imageby leveraging massive well-annotated single-scene images. The proposed networkconsists of three key components: 1) a prototype learning module, 2) aprototype-inhabiting external memory, and 3) a multi-head attention-basedmemory retrieval module. To be more specific, we first learn the prototyperepresentation of each aerial scene from single-scene aerial image datasets andstore it in an external memory. Afterwards, a multi-head attention-based memoryretrieval module is devised to retrieve scene prototypes relevant to querymulti-scene images for final predictions. Notably, only a limited number ofannotated multi-scene images are needed in the training phase. To facilitatethe progress of aerial scene recognition, we produce a new multi-scene aerialimage (MAI) dataset. Experimental results on variant dataset configurationsdemonstrate the effectiveness of our network. Our dataset and codes arepublicly available.

Aerial Scene Understanding in The Wild: Multi-Scene Recognition via Prototype-based Memory Networks