Scene Text Recognition (STR) models have achieved high performance in re...
Despite recent progress in video and language representation learning, t...
Recent efforts within the AI community have yielded impressive results
t...
In traditional Visual Question Generation (VQG), most images have multip...
Data augmentation is an approach that can effectively improve the perfor...
This paper addresses the problem of simultaneous machine translation (Si...
Conventional models for Visual Question Answering (VQA) explore determin...
In this paper, we teach machines to understand visuals and natural langu...
Deep learning approaches for Visual-Inertial Odometry (VIO) have proven
...
Due to the sparse rewards and high degree of environment variation,
rein...
Inertial information processing plays a pivotal role in ego-motion aware...
Humans are able to make rich predictions about the future dynamics of
ph...
Matrix factorization has now become a dominant solution for personalized...
Topic models have been widely explored as probabilistic generative model...
Developing a dialogue agent that is capable of making autonomous decisio...
In this work we explore deep generative models of text in which the late...
Recent advances in neural variational inference have spawned a renaissan...
This paper presents novel Bayesian optimisation algorithms for minimum e...