Related papers: Auto-labelling of Markers in Optical Motion Captur…

To recognize an object in an image, the user must apply a combination of operators, where each operator has a set of parameters. These parameters must be well adjusted in order to reach good results. Usually, this adjustment is made…

Effective leveraging of real-world driving datasets is crucial for enhancing the training of autonomous driving systems. While Offline Reinforcement Learning enables training autonomous vehicles with such data, most available datasets lack…

Automatic portrait video matting is an under-constrained problem. Most state-of-the-art methods only exploit the semantic information and process each frame individually. Their performance is compromised due to the lack of temporal…

Animation data is often obtained through optical motion capture systems, which utilize a multitude of cameras to establish the position of optical markers. However, system errors or occlusions can result in missing markers, the manual…

Deep learning models for semantic segmentation rely on expensive, large-scale, manually annotated datasets. Labelling is a tedious process that can take hours per image. Automatically annotating video sequences by propagating sparsely…

The assumption that response and predictor belong to the same statistical unit may be violated in practice. Unbiased estimation and recovery of true label ordering based on unlabeled data are challenging tasks and have attracted increasing…

In robotic applications, we often face the challenge of discovering new objects while having very little or no labelled training data. In this paper we explore the use of self-supervision provided by a robot traversing an environment to…

Uncertainty in machine learning models is a timely and vast field of research. In supervised learning, uncertainty can already occur in the first stage of the training process, the annotation phase. This scenario is particularly evident…

In the past few years we have seen great advances in object perception (particularly in 4D space-time dimensions) thanks to deep learning methods. However, they typically rely on large amounts of high-quality labels to achieve good…

Recently, as an effective way of learning latent representations, contrastive learning has been increasingly popular and successful in various domains. The success of constrastive learning in single-label classifications motivates us to…

We address the problem of vehicle self-localization from multi-modal sensor information and a reference map. The map is generated off-line by extracting landmarks from the vehicle's field of view, while the measurements are collected…

Planar markers are useful in robotics and computer vision for mapping and localisation. Given a detected marker in an image, a frequent task is to estimate the 6DOF pose of the marker relative to the camera, which is an instance of planar…

We propose a method to annotate segmentation masks accurately and automatically using invisible marker for object manipulation. Invisible marker is invisible under visible (regular) light conditions, but becomes visible under invisible…

Classification algorithms aim to predict an unknown label (e.g., a quality class) for a new instance (e.g., a product). Therefore, training samples (instances and labels) are used to deduct classification hypotheses. Often, it is relatively…

We have seen significant leapfrog advancement in machine learning in recent decades. The central idea of machine learnability lies on constructing learning algorithms that learn from good data. The availability of more data being made…

The success of state-of-the-art deep neural networks heavily relies on the presence of large-scale labelled datasets, which are extremely expensive and time-consuming to annotate. This paper focuses on tackling semi-supervised part…

Learned object detection methods based on fusion of LiDAR and camera data require labeled training samples, but niche applications, such as warehouse robotics or automated infrastructure, require semantic classes not available in large…

Manipulation actions transform objects from an initial state into a final state. In this paper, we report on the use of object state transitions as a mean for recognizing manipulation actions. Our method is inspired by the intuition that…

The use of machine learning for building a classifier in signal processing for motion sensing presents unique challenges. This paper proposes a novel method that effectively addresses the combination of skewed data sets and optimization…

This work proposes a process for efficiently training a point-wise object detector that enables localizing objects and computing their 6D poses in cluttered and occluded scenes. Accurate pose estimation is typically a requirement for robust…