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

Humans possess the cognitive ability to comprehend scenes in a compositionalmanner. To empower AI systems with similar capabilities, object-centriclearning aims to acquire representations of individual objects from visualscenes without any supervision. Although recent advances in object-centriclearning have made remarkable progress on complex synthesis datasets, there isa huge challenge for application to complex real-world scenes. One of theessential reasons is the scarcity of real-world datasets specifically tailoredto object-centric learning. To address this problem, we propose a versatilereal-world dataset of tabletop scenes for object-centric learning calledOCTScenes, which is meticulously designed to serve as a benchmark forcomparing, evaluating, and analyzing object-centric learning methods. OCTScenescontains 5000 tabletop scenes with a total of 15 objects. Each scene iscaptured in 60 frames covering a 360-degree perspective. Consequently,OCTScenes is a versatile benchmark dataset that can simultaneously satisfy theevaluation of object-centric learning methods based on single-image, video, andmulti-view. Extensive experiments of representative object-centric learningmethods are conducted on OCTScenes. The results demonstrate the shortcomings ofstate-of-the-art methods for learning meaningful representations fromreal-world data, despite their impressive performance on complex synthesisdatasets. Furthermore, OCTScenes can serve as a catalyst for the advancement ofexisting methods, inspiring them to adapt to real-world scenes. Dataset andcode are available at https://huggingface.co/datasets/Yinxuan/OCTScenes.

OCTScenes: A Versatile Real-World Dataset of Tabletop Scenes for Object-Centric Learning