Matches in SemOpenAlex for { <https://semopenalex.org/work/W3174335067> ?p ?o ?g. }
- W3174335067 abstract "ABSTRACT Crowdsourced social media data has become popular in the assessment of cultural ecosystem services (CES). Advances in deep learning show great potential for the timely assessment of CES at large scales. Here, we describe a procedure for automating the assessment of image elements pertaining to CES from social media. We focus on a binary (natural, human) and a multiclass (posing, species, nature, landscape, human activities, human structures) classification of those elements using two Convolutional Neural Networks (CNNs; VGG16 and ResNet152) with the weights from two large datasets - Places365 and ImageNet -, and our own dataset. We train those CNNs over Flickr and Wikiloc images from the Peneda-Gerês region (Portugal) and evaluate their transferability to wider areas, using Sierra Nevada (Spain) as test. CNNs trained for Peneda-Gerês performed well, with results for the binary classification (F1-score > 80%) exceeding those for the multiclass classification (> 60%). CNNs pre-trained with Places365 and ImageNet data performed significantly better than with our data. Model performance decreased when transferred to Sierra Nevada, but their performances were satisfactory (> 60%). The combination of manual annotations, freely available CNNs and pre-trained local datasets thereby show great relevance to support automated CES assessments from social media." @default.
- W3174335067 created "2021-07-05" @default.
- W3174335067 creator A5030055139 @default.
- W3174335067 creator A5036736840 @default.
- W3174335067 creator A5044139820 @default.
- W3174335067 creator A5051064654 @default.
- W3174335067 creator A5057876711 @default.
- W3174335067 creator A5073038139 @default.
- W3174335067 creator A5088780490 @default.
- W3174335067 date "2021-06-23" @default.
- W3174335067 modified "2023-10-16" @default.
- W3174335067 title "Deep learning assessment of cultural ecosystem services from social media images" @default.
- W3174335067 cites W1158588076 @default.
- W3174335067 cites W1988187608 @default.
- W3174335067 cites W2118023920 @default.
- W3174335067 cites W2153779825 @default.
- W3174335067 cites W2162873750 @default.
- W3174335067 cites W2194775991 @default.
- W3174335067 cites W2248250270 @default.
- W3174335067 cites W2290551858 @default.
- W3174335067 cites W2462222518 @default.
- W3174335067 cites W2465734108 @default.
- W3174335067 cites W2526645698 @default.
- W3174335067 cites W2550092082 @default.
- W3174335067 cites W2560297765 @default.
- W3174335067 cites W2574023341 @default.
- W3174335067 cites W2593699006 @default.
- W3174335067 cites W2702502168 @default.
- W3174335067 cites W2737525190 @default.
- W3174335067 cites W2739795267 @default.
- W3174335067 cites W2754817565 @default.
- W3174335067 cites W2764242590 @default.
- W3174335067 cites W2777417212 @default.
- W3174335067 cites W2802220769 @default.
- W3174335067 cites W2802953454 @default.
- W3174335067 cites W2885150722 @default.
- W3174335067 cites W2891691398 @default.
- W3174335067 cites W2911555398 @default.
- W3174335067 cites W2914389667 @default.
- W3174335067 cites W2935057829 @default.
- W3174335067 cites W2939877284 @default.
- W3174335067 cites W2940958671 @default.
- W3174335067 cites W2946956051 @default.
- W3174335067 cites W2954276333 @default.
- W3174335067 cites W2954932437 @default.
- W3174335067 cites W2991744714 @default.
- W3174335067 cites W2996784990 @default.
- W3174335067 cites W3014154663 @default.
- W3174335067 cites W3015226025 @default.
- W3174335067 cites W3033579499 @default.
- W3174335067 cites W3037664009 @default.
- W3174335067 cites W3038699438 @default.
- W3174335067 cites W3049555803 @default.
- W3174335067 cites W3082022019 @default.
- W3174335067 cites W3093414036 @default.
- W3174335067 cites W3098918608 @default.
- W3174335067 cites W4246406086 @default.
- W3174335067 cites W4249513657 @default.
- W3174335067 cites W4298212933 @default.
- W3174335067 doi "https://doi.org/10.1101/2021.06.23.449176" @default.
- W3174335067 hasPublicationYear "2021" @default.
- W3174335067 type Work @default.
- W3174335067 sameAs 3174335067 @default.
- W3174335067 citedByCount "1" @default.
- W3174335067 countsByYear W31743350672023 @default.
- W3174335067 crossrefType "posted-content" @default.
- W3174335067 hasAuthorship W3174335067A5030055139 @default.
- W3174335067 hasAuthorship W3174335067A5036736840 @default.
- W3174335067 hasAuthorship W3174335067A5044139820 @default.
- W3174335067 hasAuthorship W3174335067A5051064654 @default.
- W3174335067 hasAuthorship W3174335067A5057876711 @default.
- W3174335067 hasAuthorship W3174335067A5073038139 @default.
- W3174335067 hasAuthorship W3174335067A5088780490 @default.
- W3174335067 hasBestOaLocation W31743350671 @default.
- W3174335067 hasConcept C108583219 @default.
- W3174335067 hasConcept C115961682 @default.
- W3174335067 hasConcept C119857082 @default.
- W3174335067 hasConcept C12267149 @default.
- W3174335067 hasConcept C136764020 @default.
- W3174335067 hasConcept C140331021 @default.
- W3174335067 hasConcept C150899416 @default.
- W3174335067 hasConcept C154945302 @default.
- W3174335067 hasConcept C158154518 @default.
- W3174335067 hasConcept C17744445 @default.
- W3174335067 hasConcept C199539241 @default.
- W3174335067 hasConcept C2522767166 @default.
- W3174335067 hasConcept C41008148 @default.
- W3174335067 hasConcept C518677369 @default.
- W3174335067 hasConcept C53533937 @default.
- W3174335067 hasConcept C61272859 @default.
- W3174335067 hasConcept C66905080 @default.
- W3174335067 hasConcept C81363708 @default.
- W3174335067 hasConcept C87335442 @default.
- W3174335067 hasConceptScore W3174335067C108583219 @default.
- W3174335067 hasConceptScore W3174335067C115961682 @default.
- W3174335067 hasConceptScore W3174335067C119857082 @default.
- W3174335067 hasConceptScore W3174335067C12267149 @default.
- W3174335067 hasConceptScore W3174335067C136764020 @default.
- W3174335067 hasConceptScore W3174335067C140331021 @default.
- W3174335067 hasConceptScore W3174335067C150899416 @default.