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

While the majority of today's object class models provide only 2D boundingboxes, far richer output hypotheses are desirable including viewpoint,fine-grained category, and 3D geometry estimate. However, models trained toprovide richer output require larger amounts of training data, preferably wellcovering the relevant aspects such as viewpoint and fine-grained categories. Inthis paper, we address this issue from the perspective of transfer learning,and design an object class model that explicitly leverages correlations betweenvisual features. Specifically, our model represents prior distributions overpermissible multi-view detectors in a parametric way -- the priors are learnedonce from training data of a source object class, and can later be used tofacilitate the learning of a detector for a target class. As we show in ourexperiments, this transfer is not only beneficial for detectors based onbasic-level category representations, but also enables the robust learning ofdetectors that represent classes at finer levels of granularity, where trainingdata is typically even scarcer and more unbalanced. As a result, we reportlargely improved performance in simultaneous 2D object localization andviewpoint estimation on a recent dataset of challenging street scenes.

Multi-View Priors for Learning Detectors from Sparse Viewpoint Data