Related papers: Modeling Human Motion with Quaternion-based Neural…

Human motion prediction aims to forecast future human poses given a prior pose sequence. The discontinuity of the predicted motion and the performance deterioration in long-term horizons are still the main challenges encountered in current…

Inertial measurement units are commonly used to estimate the attitude of moving objects. Numerous nonlinear filter approaches have been proposed for solving the inherent sensor fusion problem. However, when a large range of different…

The modeling of human motion using machine learning methods has been widely studied. In essence it is a time-series modeling problem involving predicting how a person will move in the future given how they moved in the past. Existing…

In spite of the great progress in human motion prediction, it is still a challenging task to predict those aperiodic and complicated motions. We believe that to capture the correlations among human body components is the key to understand…

The primary goal of skeletal motion prediction is to generate future motion by observing a sequence of 3D skeletons. A key challenge in motion prediction is the fact that a motion can often be performed in several different ways, with each…

Skeleton-based human action recognition has recently attracted increasing attention due to the popularity of 3D skeleton data. One main challenge lies in the large view variations in captured human actions. We propose a novel view…

Deploying deep neural networks on edge devices is often limited by the memory traffic and compute cost of dense linear operators. While quaternion neural networks improve parameter efficiency by coupling multiple channels through Hamilton…

Multi-person pose estimation in images and videos is an important yet challenging task with many applications. Despite the large improvements in human pose estimation enabled by the development of convolutional neural networks, there still…

The task of predicting human motion is complicated by the natural heterogeneity and compositionality of actions, necessitating robustness to distributional shifts as far as out-of-distribution (OoD). Here we formulate a new OoD benchmark…

Recovering 3D human pose from 2D joints is a highly unconstrained problem. We propose a novel neural network framework, PoseNet3D, that takes 2D joints as input and outputs 3D skeletons and SMPL body model parameters. By casting our…

Existing skeleton-based 3D human pose estimation methods only predict joint positions. Although the yaw and pitch of bone rotations can be derived from joint positions, the roll around the bone axis remains unresolved. We present…

We develop a robust quaternion recurrent neural network (QRNN) for real-time processing of 3D and 4D data with outliers. This is achieved by combining the real-time recurrent learning (RTRL) algorithm and the maximum correntropy criterion…

Knee injuries are frequent, varied and often require the patient to undergo intensive rehabilitation for several months. Treatment protocols usually contemplate some recurrent measurements in order to assess progress, such as goniometry.…

Recently, graph neural networks (GNNs) have become an important and active research direction in deep learning. It is worth noting that most of the existing GNN-based methods learn graph representations within the Euclidean vector space.…

Human motion prediction is essential for the safe and smooth operation of mobile service robots and intelligent vehicles around people. Commonly used neural network-based approaches often require large amounts of complete trajectories to…

Deep Convolutional Neural Networks (DCNN) have been proven to be effective for various computer vision problems. In this work, we demonstrate its effectiveness on a continuous object orientation estimation task, which requires prediction of…

Predicting human trajectory is crucial for social robot navigation in crowded environments. While most existing approaches treat human as point mass, we present a study on multi-agent trajectory prediction that leverages different human…

Following the success of deep convolutional networks, state-of-the-art methods for 3d human pose estimation have focused on deep end-to-end systems that predict 3d joint locations given raw image pixels. Despite their excellent performance,…

Most recent approaches to monocular 3D pose estimation rely on Deep Learning. They either train a Convolutional Neural Network to directly regress from image to 3D pose, which ignores the dependencies between human joints, or model these…

In this paper, we present an adaptation of the sequence-to-sequence model for structured output prediction in vision tasks. In this model the output variables for a given input are predicted sequentially using neural networks. The…