Search Results for author:
Found 9 papers, 2 papers with code
GCNext: Towards the Unity of Graph Convolutions for Human Motion Prediction
The past few years has witnessed the dominance of Graph Convolutional Networks (GCNs) over human motion prediction. Various styles of graph convolutions have been proposed, with each one meticulously designed and incorporated into a carefully-crafted network architecture.
Expressive Forecasting of 3D Whole-body Human Motions
Human motion forecasting, with the goal of estimating future human behavior over a period of time, is a fundamental task in many real-world applications.
Learning Snippet-to-Motion Progression for Skeleton-based Human Motion Prediction
Existing Graph Convolutional Networks to achieve human motion prediction largely adopt a one-step scheme, which output the prediction straight from history input, failing to exploit human motion patterns.
Meta-Auxiliary Learning for Adaptive Human Pose Prediction
Predicting high-fidelity future human poses, from a historically observed sequence, is decisive for intelligent robots to interact with humans.
Graph-Guided MLP-Mixer for Skeleton-Based Human Motion Prediction
In recent years, Graph Convolutional Networks (GCNs) have been widely used in human motion prediction, but their performance remains unsatisfactory.
Ranked #3 on
Human Pose Forecasting
on Human3.6M
Test-time Personalizable Forecasting of 3D Human Poses
Current motion forecasting approaches typically train a deep end-to-end model from the source domain data, and then apply it directly to target subjects.
Overlooked Poses Actually Make Sense: Distilling Privileged Knowledge for Human Motion Prediction
Previous works on human motion prediction follow the pattern of building a mapping relation between the sequence observed and the one to be predicted.
Towards Accurate 3D Human Motion Prediction From Incomplete Observations
Specifically, the model involves two branches, in which the primary task is to focus on forecasting future 3D human actions accurately, while the auxiliary one is to repair the missing value of the incomplete observation.
Learning Dynamic Relationships for 3D Human Motion Prediction
Specifically, the skeleton pose is represented as a novel dynamic graph, in which natural connectivities of the joint pairs are exploited explicitly, and the links of geometrically separated joints can also be learned implicitly.
