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

In object recognition, Fisher vector (FV) representation is one of thestate-of-art image representations ways at the expense of dense, highdimensional features and increased computation time. A simplification of FV isattractive, so we propose Sparse Fisher vector (SFV). By incorporating localitystrategy, we can accelerate the Fisher coding step in image categorizationwhich is implemented from a collective of local descriptors. Combining withpooling step, we explore the relationship between coding step and pooling stepto give a theoretical explanation about SFV. Experiments on benchmark datasetshave shown that SFV leads to a speedup of several-fold of magnitude compareswith FV, while maintaining the categorization performance. In addition, wedemonstrate how SFV preserves the consistence in representation of similarlocal features.

Efficient Image Categorization with Sparse Fisher Vector