Despite remarkable recent advances, making object-centric learning work ...
In this paper, we propose a novel object-centric representation, called
...
Unsupervised object-centric learning aims to represent the modular,
comp...
Object-centric world models provide structured representation of the sce...
When tasks change over time, meta-transfer learning seeks to improve the...
The ability to decompose complex multi-object scenes into meaningful
abs...
Neural processes combine the strengths of neural networks and Gaussian
p...
Guided troubleshooting is an inherent task in the domain of technical su...
Vast availability of text data has enabled widespread training and use o...
In scenarios involving text classification where the number of classes i...
Ontologies in different natural languages often differ in quality in ter...