ehjhihlo

MotionAGFormer

Official implementation of the paper "MotionAGFormer: Enhancing 3D Pose Estimation with a Transformer-GCNFormer Network" (WACV 2024).

OadTR

Code for our ICCV 2021 Paper "OadTR: Online Action Detection with Transformers".

EpipolarPose

Self-Supervised Learning of 3D Human Pose using Multi-view Geometry (CVPR2019)

HyperPose

Library for Fast and Flexible Human Pose Estimation

HybrIK

Official code of "HybrIK: A Hybrid Analytical-Neural Inverse Kinematics Solution for 3D Human Pose and Shape Estimation", CVPR 2021

mRI

Data repo for mRI: Multi-modal 3D Human Pose Estimation Dataset using mmWave, RGB-D, and Inertial Sensors

ICLab-2023

Spring 2023 NYCU (prev. NCTU) Integrated Circuit Design Laboratory (ICLab)

MiniROAD

MAT-Memory-and-Anticipation-Transformer

[ICCV 2023] Official implementation of Memory-and-Anticipation Transformer for Online Action Understanding

D3DP

[ICCV2023] The PyTorch implementation for "Diffusion-Based 3D Human Pose Estimation with Multi-Hypothesis Aggregation"

DiffPose

TriDet

[CVPR2023] Code for the paper, TriDet: Temporal Action Detection with Relative Boundary Modeling

lightweight-human-pose-estimation-3d-demo.pytorch

Real-time 3D multi-person pose estimation demo in PyTorch. OpenVINO backend can be used for fast inference on CPU.

skeleton-pose

DC-GCT

probabilistic_triangulation

Probabilistic triangulation module applied to uncalibrated human pose estimation

fewshotQAT

[BMVC 2021]: Official PyTorch implementation of : "Few Shot Temporal Action Localization using Query Adaptive Transformers"

Realtime-Action-Recognition

Apply ML to the skeletons from OpenPose; 9 actions; multiple people. (WARNING: I'm sorry that this is only good for course demo, not for real world applications !!! Those ary very difficult !!!)

ACM-Net

The official repository of our paper "ACM-Net: Action Context Modeling Network for Weakly-Supervised Temporal Action Localization".

YOWOF

You Only Watch One Frame for Online Spatio-Temporal Action Detection

VideoPose3D

Efficient 3D human pose estimation in video using 2D keypoint trajectories

slam-python

SLAM - Simultaneous localization and mapping using OpenCV and NumPy.

ASM-Loc

(CVPR2022) ASM-Loc: Action-aware Segment Modeling for Weakly-Supervised Temporal Action Localization

ActionMAE

[AAAI 2023] Official pytorch implementation of "Towards Good Practices for Missing Modality Robust Action Recognition"

CO2A

TranSVAE

[NeurIPS 2023] Unsupervised Video Domain Adaptation for Action Recognition: A Disentanglement Perspective

MME

official implementation of CVPR 23 paper "M3Video: Masked Motion Modeling for Self-Supervised Video Representation Learning"

mvd

[CVPR2023] Masked Video Distillation: Rethinking Masked Feature Modeling for Self-supervised Video Representation Learning (https://arxiv.org/abs/2212.04500)

BIKE

【CVPR'2023】Bidirectional Cross-Modal Knowledge Exploration for Video Recognition with Pre-trained Vision-Language Models

DiffusionTAD

[ICCV 2023] Official PyTorch implementation of the paper "DiffTAD: Temporal Action Detection with Proposal Denoising Diffusion"