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 the task of Object Recognition, there exists a dichotomy between thecategorization of objects and estimating object pose, where the formernecessitates a view-invariant representation, while the latter requires arepresentation capable of capturing pose information over different categoriesof objects. With the rise of deep architectures, the prime focus has been onobject category recognition. Deep learning methods have achieved wide successin this task. In contrast, object pose regression using these approaches hasreceived relatively much less attention. In this paper we show how deeparchitectures, specifically Convolutional Neural Networks (CNN), can be adaptedto the task of simultaneous categorization and pose estimation of objects. Weinvestigate and analyze the layers of various CNN models and extensivelycompare between them with the goal of discovering how the layers of distributedrepresentations of CNNs represent object pose information and how thiscontradicts with object category representations. We extensively experiment ontwo recent large and challenging multi-view datasets. Our models achieve betterthan state-of-the-art performance on both datasets.

Convolutional Models for Joint Object Categorization and Pose Estimation