Related papers: Learning Keypoints from Synthetic Data for Robotic…

Goal-conditioned rearrangement of deformable objects (e.g. straightening a rope and folding a cloth) is one of the most common deformable manipulation tasks, where the robot needs to rearrange a deformable object into a prescribed goal…

The gesture recognition using motion capture data and depth sensors has recently drawn more attention in vision recognition. Currently most systems only classify dataset with a couple of dozens different actions. Moreover, feature…

Many robotic tasks are still teleoperated since automating them is very time consuming and expensive. Robot Learning from Demonstrations (RLfD) can reduce programming time and cost. However, conventional RLfD approaches are not directly…

In the last few years, we have witnessed the rise of a series of deep learning methods to generate synthetic images that look extremely realistic. These techniques prove useful in the movie industry and for artistic purposes. However, they…

Deep neural networks, albeit their great success on feature learning in various computer vision tasks, are usually considered as impractical for online visual tracking because they require very long training time and a large number of…

Deep learning has demonstrated remarkable capabilities in simulating complex dynamic systems. However, existing methods require known physical properties as supervision or inputs, limiting their applicability under unknown conditions. To…

Recently, outstanding identification rates in image classification tasks were achieved by convolutional neural networks (CNNs). to use such skills, selective CNNs trained on a dataset of well-known images of metal surface defects captured…

Deep learning methods have recently exhibited impressive performance in object detection. However, such methods needed much training data to achieve high recognition accuracy, which was time-consuming and required considerable manual work…

Collecting high-quality data for training large-scale robotic models typically relies on real robot platforms, which is labor-intensive and costly, whether via teleoperation or scripted demonstrations. To scale data collection, many…

Comparing robotic cloth-manipulation systems in a real-world setup is challenging. The fidelity gap between simulation-trained cloth neural controllers and real-world operation hinders the reliable deployment of these methods in physical…

As one of the fundamental techniques for image editing, image cropping discards unrelevant contents and remains the pleasing portions of the image to enhance the overall composition and achieve better visual/aesthetic perception. In this…

A robot's ability to act is fundamentally constrained by what it can perceive. Many existing approaches to visual representation learning utilize general-purpose training criteria, e.g. image reconstruction, smoothness in latent space, or…

To train well-performing generalizing neural networks, sufficiently large and diverse datasets are needed. Collecting data while adhering to privacy legislation becomes increasingly difficult and annotating these large datasets is both a…

Cloth manipulation is a ubiquitous task in everyday life, but it remains an open challenge for robotics. The difficulties in developing cloth manipulation policies are attributed to the high-dimensional state space, complex dynamics, and…

Understanding of deformable object manipulations such as textiles is a challenge due to the complexity and high dimensionality of the problem. Particularly, the lack of a generic representation of semantic states (e.g., \textit{crumpled},…

A significant problem of using deep learning techniques is the limited amount of data available for training. There are some datasets available for the popular problems like item recognition and classification or self-driving cars, however,…

High-resolution fingerprint recognition often relies on sophisticated matching algorithms based on hand-crafted keypoint descriptors, with pores being the most common keypoint choice. Our method is the opposite of the prevalent approach: we…

In this paper, we propose a novel deep neural network framework embedded with low-level features (LCNN) for salient object detection in complex images. We utilise the advantage of convolutional neural networks to automatically learn the…

Convolutional neural networks (CNNs) have been recently used for a variety of histology image analysis. However, availability of a large dataset is a major prerequisite for training a CNN which limits its use by the computational pathology…

Discriminative features are critical for machine learning applications. Most existing deep learning approaches, however, rely on convolutional neural networks (CNNs) for learning features, whose discriminant power is not explicitly…