Stars
The official pytorch implemention of our ICML-2021 paper "SimAM: A Simple, Parameter-Free Attention Module for Convolutional Neural Networks".
A concise but complete full-attention transformer with a set of promising experimental features from various papers
This is the official implementation of the paper "A Neural Network Approach to Missing Marker Reconstruction in Human Motion Capture"
code for the paper "AMHGCN: Adaptive Multi-level Hypergraph Convolution Network for Human Motion Prediction"
[ECCV 2022 oral] Official PyTorch implementation of the paper "Diverse Human Motion Prediction Guided by Multi-Level Spatial-Temporal Anchors"
Source code of paper "Convolutional Sequence to Sequence Model for Human Dynamics"
Python script for rendering 3D human poses using Blender
code for the paper "Class-guided Human Motion Prediction via Multi-spatial-temporal Supervision"
The Official Pytorch Implementation of DSTD-GCN. (TNNLS 2023)
Official implementation of the paper: CISTGCN - Context-based Interpretable Spatio-Temporal Graph Convolutional Network for Human Motion Forecasting
[ICCV2023] Official PyTorch Implementation of "BeLFusion: Latent Diffusion for Behavior-Driven Human Motion Prediction". ICCV 2023
Official implementation for the paper: Generating Smooth Pose Sequences for Diverse Human Motion Prediction
A Spatio-temporal Transformer for 3D Human Motion Prediction
[ICCV2023] Auxiliary Tasks Benefit 3D Skeleton-based Human Motion Prediction
KD-Former: kinematic and dynamic Coupled Transformer Network for 3D Human Motion Prediction
[ECCV 2020] Official PyTorch Implementation of "DLow: Diversifying Latent Flows for Diverse Human Motion Prediction". ECCV 2020.
PredictiveMA-WGAN to predict human motion using 3D skeletons
This repository implement the code behind HP-GAN paper (https://arxiv.org/abs/1711.09561).
code for the paper "A human-like action learning process: Progressive pose generation for motion prediction"