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

Despite the recent successes in computer vision, there remain new avenues toexplore. In this work, we propose a new dataset to investigate the effect ofself-occlusion on deep neural networks. With TEOS (The Effect ofSelf-Occlusion), we propose a 3D blocks world dataset that focuses on thegeometric shape of 3D objects and their omnipresent challenge ofself-occlusion. We designed TEOS to investigate the role of self-occlusion inthe context of object classification. Even though remarkable progress has beenseen in object classification, self-occlusion is a challenge. In thereal-world, self-occlusion of 3D objects still presents significant challengesfor deep learning approaches. However, humans deal with this by deployingcomplex strategies, for instance, by changing the viewpoint or manipulating thescene to gather necessary information. With TEOS, we present a dataset of twodifficulty levels (L1 and L2 ), containing 36 and 12 objects, respectively. Weprovide 738 uniformly sampled views of each object, their mask, object andcamera position, orientation, amount of self-occlusion, as well as the CADmodel of each object. We present baseline evaluations with five well-knownclassification deep neural networks and show that TEOS poses a significantchallenge for all of them. The dataset, as well as the pre-trained models, aremade publicly available for the scientific community underhttps://nvision2.data.eecs.yorku.ca/TEOS.

Blocks World Revisited: The Effect of Self-Occlusion on Classification by Convolutional Neural Networks