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

Deep learning with a convolutional neural network (CNN) has been proved to bevery effective in feature extraction and representation of images. For imageclassification problems, this work aim at finding which classifier is morecompetitive based on high-level deep features of images. In this report, wehave discussed the nearest neighbor, support vector machines and extremelearning machines for image classification under deep convolutional activationfeature representation. Specifically, we adopt the benchmark object recognitiondataset from multiple sources with domain bias for evaluating differentclassifiers. The deep features of the object dataset are obtained by awell-trained CNN with five convolutional layers and three fully-connectedlayers on the challenging ImageNet. Experiments demonstrate that the ELMsoutperform SVMs in cross-domain recognition tasks. In particular,state-of-the-art results are obtained by kernel ELM which outperforms SVMs withabout 4% of the average accuracy. The features and codes are available inhttp://www.escience.cn/people/lei/index.html

SVM and ELM: Who Wins? Object Recognition with Deep Convolutional Features from ImageNet