A household robot should be able to navigate to target locations without...
Multimodal learning considers learning from multi-modality data, aiming ...
The perception system in personalized mobile agents requires developing
...
Novel object captioning (NOC) aims to describe images containing objects...
Recent developments in self-supervised learning give us the possibility ...
We argue that a form of the valuable information provided by the auxilia...
Conditional contrastive learning frameworks consider the conditional sam...
Self-supervised approaches for speech representation learning are challe...
This paper presents to integrate the auxiliary information (e.g., additi...
Self-supervised learning is a form of unsupervised learning that leverag...
In this report, we relate the algorithmic design of Barlow Twins' method...
This paper introduces Relative Predictive Coding (RPC), a new contrastiv...
Advances in visual navigation methods have led to intelligent embodied
n...
Self-supervised representation learning adopts self-defined signals as
s...
Since its inception, the neural estimation of mutual information (MI) ha...
Optimal transport is a machine learning technique with applications incl...
The human language has heterogeneous sources of information, including t...
We introduce a new routing algorithm for capsule networks, in which a ch...
While deep learning has received a surge of interest in a variety of fie...
Estimating mutual information is an important machine learning and stati...
Transformer is a powerful architecture that achieves superior performanc...
Feed-forward neural networks can be understood as a combination of an
in...
There has been an increased interest in multimodal language processing
i...
Human language is often multimodal, which comprehends a mixture of natur...
Human language is a rich multimodal signal consisting of spoken words, f...
Visual relationship reasoning is a crucial yet challenging task for
unde...
Learning representations of multimodal data is a fundamentally complex
r...
Measuring divergence between two distributions is essential in machine
l...
"Which Generative Adversarial Networks (GANs) generates the most plausib...
Recent works investigated the generalization properties in deep neural
n...
Many of the existing methods for learning joint embedding of images and ...