Kien Nguyen's repositories
KinematicNet
Kinematic Estimation from Multi-View Images
adagraph
PyTorch implementation of AdaGraph: Unifying Predictive and Continuous Domain Adaptation through Graphs
TRO
The Pytorch implementation for "Topology-aware Distributionally Robust Optimization" (ICLR 2023)
CIDA
[ICML 2020] Continuously Indexed Domain Adaptation
cotta
[CVPR 2022] CoTTA Code for our CVPR 2022 paper Continual Test-Time Domain Adaptation
DomainBed
DomainBed is a suite to test domain generalization algorithms
EAML
Code Release for Learning to Adapt to Evolving Domains
GRDA
[ICLR 2022] Graph-Relational Domain Adaptation
hmr
Project page for End-to-end Recovery of Human Shape and Pose
I2L-MeshNet_RELEASE
Official PyTorch implementation of "I2L-MeshNet: Image-to-Lixel Prediction Network for Accurate 3D Human Pose and Mesh Estimation from a Single RGB Image", ECCV 2020
LAME
This code accompanies the paper "Parameter-free Online Test-time Adaptation".
learnable-triangulation-pytorch
This repository is an official PyTorch implementation of the paper "Learnable Triangulation of Human Pose" (ICCV 2019, oral). Proposed method archives state-of-the-art results in multi-view 3D human pose estimation!
LSSAE
The official implementation of paper "Generalizing to Evolving Domains with Latent Structure-Aware Sequential Autoencoder"
Nyquixt.github.io
A beautiful, simple, clean, and responsive Jekyll theme for academics
pytorch-cifar
95.47% on CIFAR10 with PyTorch
QuaterNet
Proposes neural networks that can generate animation of virtual characters for different actions.
smplify-x
Expressive Body Capture: 3D Hands, Face, and Body from a Single Image
TENT
ICLR21 Tent: Fully Test-Time Adaptation by Entropy Minimization
TTAC
Code for "Revisiting Realistic Test-Time Training: Sequential Inference and Adaptation by Anchored Clustering"
UniPose
We propose UniPose, a unified framework for human pose estimation, based on our “Waterfall” Atrous Spatial Pooling architecture, that achieves state-of-art-results on several pose estimation metrics. Current pose estimation methods utilizing standard CNN architectures heavily rely on statistical postprocessing or predefined anchor poses for joint localization. UniPose incorporates contextual seg- mentation and joint localization to estimate the human pose in a single stage, with high accuracy, without relying on statistical postprocessing methods. The Waterfall module in UniPose leverages the efficiency of progressive filter- ing in the cascade architecture, while maintaining multi- scale fields-of-view comparable to spatial pyramid config- urations. Additionally, our method is extended to UniPose- LSTM for multi-frame processing and achieves state-of-the- art results for temporal pose estimation in Video. Our re- sults on multiple datasets demonstrate that UniPose, with a ResNet backbone and Waterfall module, is a robust and efficient architecture for pose estimation obtaining state-of- the-art results in single person pose detection for both sin- gle images and videos.
variational-beam-search
Code repository of NeurIPS 2021 paper: Detecting and Adapting to Irregular Distribution Shifts in Bayesian Online Learning.