Related papers: Self-supervised Body Image Acquisition Using a Dee…

Human learning and intelligence work differently from the supervised pattern recognition approach adopted in most deep learning architectures. Humans seem to learn rich representations by exploration and imitation, build causal models of…

This paper introduces Action Image, a new grasp proposal representation that allows learning an end-to-end deep-grasping policy. Our model achieves $84\%$ grasp success on $172$ real world objects while being trained only in simulation on…

In computational reinforcement learning, a growing body of work seeks to construct an agent's perception of the world through predictions of future sensations; predictions about environment observations are used as additional input features…

This paper proposes the first self-supervised 6D object pose prediction from multimodal RGB+polarimetric images. The novel training paradigm comprises 1) a physical model to extract geometric information of polarized light, 2) a…

This article proposes an architecture, which allows the prediction of intention by internally simulating perceptual states represented by action pattern vectors. To this end, associative self-organising neural networks (A-SOM) is utilised…

Humans make extensive use of vision and touch as complementary senses, with vision providing global information about the scene and touch measuring local information during manipulation without suffering from occlusions. While prior work…

How can a machine learn to recognize visual attributes emerging out of online community without a definitive supervised dataset? This paper proposes an automatic approach to discover and analyze visual attributes from a noisy collection of…

We propose HyperDynamics, a dynamics meta-learning framework that conditions on an agent's interactions with the environment and optionally its visual observations, and generates the parameters of neural dynamics models based on inferred…

Self-supervised learning for image denoising problems in the presence of denaturation for noisy data is a crucial approach in machine learning. However, theoretical understanding of the performance of the approach that uses denatured data…

We present a method to analyze images taken from a passive egocentric wearable camera along with the contextual information, such as time and day of week, to learn and predict everyday activities of an individual. We collected a dataset of…

Instance segmentation of unknown objects from images is regarded as relevant for several robot skills including grasping, tracking and object sorting. Recent results in computer vision have shown that large hand-labeled datasets enable high…

Automating the analysis of surveillance video footage is of great interest when urban environments or industrial sites are monitored by a large number of cameras. As anomalies are often context-specific, it is hard to predefine events of…

Predicting human performance in interaction tasks allows designers or developers to understand the expected performance of a target interface without actually testing it with real users. In this work, we present a deep neural net to model…

To take full advantage of fast-growing unlabeled networked data, this paper introduces a novel self-supervised strategy for graph representation learning by exploiting natural supervision provided by the data itself. Inspired by human…

Neural networks are a powerful framework for foreground segmentation in video acquired by static cameras, segmenting moving objects from the background in a robust way in various challenging scenarios. The premier methods are those based on…

Accurate traffic participant prediction is the prerequisite for collision avoidance of autonomous vehicles. In this work, we predict pedestrians by emulating their own motion planning. From online observations, we infer a mixture density…

In order to operate autonomously, a robot should explore the environment and build a model of each of the surrounding objects. A common approach is to carefully scan the whole workspace. This is time-consuming. It is also often impossible…

The problem of estimating event truths from conflicting agent opinions in a social network is investigated. An autoencoder learns the complex relationships between event truths, agent reliabilities and agent observations. A Bayesian network…

Deep artificial neural networks (DNNs) trained through backpropagation provide effective models of the mammalian visual system, accurately capturing the hierarchy of neural responses through primary visual cortex to inferior temporal cortex…

The question of whether deep neural networks are good at generalising beyond their immediate training experience is of critical importance for learning-based approaches to AI. Here, we consider tests of out-of-sample generalisation that…