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

Learning binary representation is essential to large-scale computer visiontasks. Most existing algorithms require a separate quantization constraint tolearn effective hashing functions. In this work, we present Direct BinaryEmbedding (DBE), a simple yet very effective algorithm to learn binaryrepresentation in an end-to-end fashion. By appending an ingeniously designedDBE layer to the deep convolutional neural network (DCNN), DBE learns binarycode directly from the continuous DBE layer activation without quantizationerror. By employing the deep residual network (ResNet) as DCNN component, DBEcaptures rich semantics from images. Furthermore, in the effort of handlingmultilabel images, we design a joint cross entropy loss that includes bothsoftmax cross entropy and weighted binary cross entropy in consideration of thecorrelation and independence of labels, respectively. Extensive experimentsdemonstrate the significant superiority of DBE over state-of-the-art methods ontasks of natural object recognition, image retrieval and image annotation.

End-to-end Binary Representation Learning via Direct Binary Embedding