相关论文: Flexible Neural Representation for Physics Predict…

To make progress in science, we often build abstract representations of physical systems that meaningfully encode information about the systems. The representations learnt by most current machine learning techniques reflect statistical…

Dynamics models learned from visual observations have shown to be effective in various robotic manipulation tasks. One of the key questions for learning such dynamics models is what scene representation to use. Prior works typically assume…

We describe how hierarchical concepts can be represented in three types of layered neural networks. The aim is to support recognition of the concepts when partial information about the concepts is presented, and also when some of the…

Our ability to interact with the world around us relies on being able to infer what actions objects afford -- often referred to as affordances. The neural mechanisms of object-action associations are realized in the visuomotor pathway where…

The motion of deformable 4D objects lies in a low-dimensional manifold. To better capture the low dimensionality and enable better controllability, traditional methods have devised several heuristic-based methods, i.e., rigging, for…

Learning physically structured representations of dynamical systems that include contact between different objects is an important problem for learning-based approaches in robotics. Black-box neural networks can learn to approximately…

Physics-based differentiable rendering (PBDR) has become an efficient method in computer vision, graphics, and machine learning for addressing an array of inverse problems. PBDR allows patterns to be generated from perceptions which can be…

Over the past few years, a significant progress has been made in deep convolutional neural networks (CNNs)-based image recognition. This is mainly due to the strong ability of such networks in mining discriminative object pose and parts…

We develop a system for modeling hand-object interactions in 3D from RGB images that show a hand which is holding a novel object from a known category. We design a Convolutional Neural Network (CNN) for Hand-held Object Pose and Shape…

Understanding what makes high-dimensional data learnable is a fundamental question in machine learning. On the one hand, it is believed that the success of deep learning lies in its ability to build a hierarchy of representations that…

The ability to interact and understand the environment is a fundamental prerequisite for a wide range of applications from robotics to augmented reality. In particular, predicting how deformable objects will react to applied forces in real…

We propose a self-supervised physics-informed neural network (PINN) framework that adaptively balances physics-based and data-driven supervision for scientific machine learning under data scarcity. Unlike prior PINNs that rely on fixed or…

Deep Learning has been shown to learn efficient representations for structured data such as image, text or audio. In this chapter, we present neural network architectures that are able to learn efficient representations of molecules and…

The objective of image manipulation detection is to identify and locate the manipulated regions in the images. Recent approaches mostly adopt the sophisticated Convolutional Neural Networks (CNNs) to capture the tampering artifacts left in…

Holistic 3D human-scene reconstruction is a crucial and emerging research area in robot perception. A key challenge in holistic 3D human-scene reconstruction is to generate a physically plausible 3D scene from a single monocular RGB image.…

Convolutional Neural Networks (CNNs) have proved exceptional at learning representations for visual object categorization. However, CNNs do not explicitly encode objects, parts, and their physical properties, which has limited CNNs' success…

Object manipulation skills are necessary for robots operating in various daily-life scenarios, ranging from warehouses to hospitals. They allow the robots to manipulate the given object to their desired arrangement in the cluttered…

This paper presents a new data-driven framework for analyzing periodic physical human-robot interaction (pHRI) in latent state space. To elaborate human understanding and/or robot control during pHRI, the model representing pHRI is…

Neural radiance fields (NeRFs) are a widely accepted standard for synthesizing new 3D object views from a small number of base images. However, NeRFs have limited generalization properties, which means that we need to use significant…

Deep learning forms a hierarchical network structure for representation of multiple input features. The adaptive structural learning method of Deep Belief Network (DBN) can realize a high classification capability while searching the…