FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3153506370> ?p ?o ?g. }

• W3153506370 abstract "Aerial scene recognition is a fundamental visual task and has attracted an increasing research interest in the last few years. Most of current researches mainly deploy efforts to categorize an aerial image into one scene-level label, while in real-world scenarios, there often exist multiple scenes in a single image. Therefore, in this paper, we propose to take a step forward to a more practical and challenging task, namely multi-scene recognition in single images. Moreover, we note that manually yielding annotations for such a task is extraordinarily time- and labor-consuming. To address this, we propose a prototype-based memory network to recognize multiple scenes in a single image by leveraging massive well-annotated single-scene images. The proposed network consists of three key components: 1) a prototype learning module, 2) a prototype-inhabiting external memory, and 3) a multi-head attention-based memory retrieval module. To be more specific, we first learn the prototype representation of each aerial scene from single-scene aerial image datasets and store it in an external memory. Afterwards, a multi-head attention-based memory retrieval module is devised to retrieve scene prototypes relevant to query multi-scene images for final predictions. Notably, only a limited number of annotated multi-scene images are needed in the training phase. To facilitate the progress of aerial scene recognition, we produce a new multi-scene aerial image (MAI) dataset. Experimental results on variant dataset configurations demonstrate the effectiveness of our network. Our dataset and codes are publicly available." @default.
• W3153506370 created "2021-04-26" @default.
• W3153506370 creator A5015941411 @default.
• W3153506370 creator A5036724788 @default.
• W3153506370 creator A5068384981 @default.
• W3153506370 creator A5083100048 @default.
• W3153506370 creator A5090543058 @default.
• W3153506370 date "2021-04-22" @default.
• W3153506370 modified "2023-10-14" @default.
• W3153506370 title "Aerial Scene Understanding in The Wild: Multi-Scene Recognition via Prototype-based Memory Networks" @default.
• W3153506370 cites W1686810756 @default.
• W3153506370 cites W1793121960 @default.
• W3153506370 cites W1953606363 @default.
• W3153506370 cites W1980038761 @default.
• W3153506370 cites W2054397552 @default.
• W3153506370 cites W2084786824 @default.
• W3153506370 cites W2097117768 @default.
• W3153506370 cites W2150593711 @default.
• W3153506370 cites W2194775991 @default.
• W3153506370 cites W2331692618 @default.
• W3153506370 cites W2510282234 @default.
• W3153506370 cites W2514312656 @default.
• W3153506370 cites W2547812480 @default.
• W3153506370 cites W2575479478 @default.
• W3153506370 cites W2593771152 @default.
• W3153506370 cites W2601450892 @default.
• W3153506370 cites W2602837914 @default.
• W3153506370 cites W2603776936 @default.
• W3153506370 cites W2727426218 @default.
• W3153506370 cites W2767407859 @default.
• W3153506370 cites W2767819622 @default.
• W3153506370 cites W2782522152 @default.
• W3153506370 cites W2787931417 @default.
• W3153506370 cites W2793461576 @default.
• W3153506370 cites W2795476700 @default.
• W3153506370 cites W2802076210 @default.
• W3153506370 cites W2804982862 @default.
• W3153506370 cites W2883589384 @default.
• W3153506370 cites W2884419823 @default.
• W3153506370 cites W2884821995 @default.
• W3153506370 cites W2897372286 @default.
• W3153506370 cites W2903382683 @default.
• W3153506370 cites W2946373483 @default.
• W3153506370 cites W2947443368 @default.
• W3153506370 cites W2947471972 @default.
• W3153506370 cites W2949351478 @default.
• W3153506370 cites W2963066447 @default.
• W3153506370 cites W2963314614 @default.
• W3153506370 cites W2963374479 @default.
• W3153506370 cites W2963403868 @default.
• W3153506370 cites W2963448850 @default.
• W3153506370 cites W2963659230 @default.
• W3153506370 cites W2963995737 @default.
• W3153506370 cites W2965868573 @default.
• W3153506370 cites W2969974902 @default.
• W3153506370 cites W2986943971 @default.
• W3153506370 cites W2988510619 @default.
• W3153506370 cites W2998601171 @default.
• W3153506370 cites W3005814862 @default.
• W3153506370 cites W3021057985 @default.
• W3153506370 cites W3034655362 @default.
• W3153506370 cites W3034915791 @default.
• W3153506370 cites W3035240825 @default.
• W3153506370 cites W3035821888 @default.
• W3153506370 cites W3036390325 @default.
• W3153506370 cites W3036416023 @default.
• W3153506370 cites W3042950341 @default.
• W3153506370 cites W3064134516 @default.
• W3153506370 cites W3092800550 @default.
• W3153506370 cites W3098824823 @default.
• W3153506370 cites W3100892511 @default.
• W3153506370 cites W3104282073 @default.
• W3153506370 cites W3105577662 @default.
• W3153506370 doi "https://doi.org/10.48550/arxiv.2104.11200" @default.
• W3153506370 hasPublicationYear "2021" @default.
• W3153506370 type Work @default.
• W3153506370 sameAs 3153506370 @default.
• W3153506370 citedByCount "0" @default.
• W3153506370 crossrefType "posted-content" @default.
• W3153506370 hasAuthorship W3153506370A5015941411 @default.
• W3153506370 hasAuthorship W3153506370A5036724788 @default.
• W3153506370 hasAuthorship W3153506370A5068384981 @default.
• W3153506370 hasAuthorship W3153506370A5083100048 @default.
• W3153506370 hasAuthorship W3153506370A5090543058 @default.
• W3153506370 hasBestOaLocation W31535063701 @default.
• W3153506370 hasConcept C115961682 @default.
• W3153506370 hasConcept C153180895 @default.
• W3153506370 hasConcept C154945302 @default.
• W3153506370 hasConcept C162324750 @default.
• W3153506370 hasConcept C17744445 @default.
• W3153506370 hasConcept C187736073 @default.
• W3153506370 hasConcept C199539241 @default.
• W3153506370 hasConcept C26517878 @default.
• W3153506370 hasConcept C2776359362 @default.
• W3153506370 hasConcept C2776429412 @default.
• W3153506370 hasConcept C2780451532 @default.
• W3153506370 hasConcept C31972630 @default.
• W3153506370 hasConcept C38652104 @default.
• W3153506370 hasConcept C41008148 @default.
• W3153506370 hasConcept C94124525 @default.

• next