Code for "Human Pose Regression with Residual Log-likelihood Estimation", ICCV 2021 Oral

Last update: Dec 24, 2022

Overview

Human Pose Regression with Residual Log-likelihood Estimation

[Paper] [arXiv] [Project Page]

Human Pose Regression with Residual Log-likelihood Estimation
Jiefeng Li, Siyuan Bian, Ailing Zeng, Can Wang, Bo Pang, Wentao Liu, Cewu Lu
ICCV 2021 Oral

Regression with Residual Log-likelihood Estimation

TODO

Provide minimal implementation of RLE loss.
Provide implementation on Human3.6M dataset.
Provide implementation on COCO dataset.

Installation

Install pytorch >= 1.1.0 following official instruction.
Install rlepose:

pip install cython
python setup.py develop

Install COCOAPI.

pip install -U 'git+https://github.com/cocodataset/cocoapi.git#subdirectory=PythonAPI'

Init data directory:

mkdir data

Download COCO data:

|-- data
`-- |-- coco
    `-- |-- annotations
        |   |-- person_keypoints_train2017.json
        |   `-- person_keypoints_val2017.json
        `-- images
            |-- train2017
            |   |-- 000000000009.jpg
            |   |-- 000000000025.jpg
            |   |-- 000000000030.jpg
            |   |-- ... 
            `-- val2017
                |-- 000000000139.jpg
                |-- 000000000285.jpg
                |-- 000000000632.jpg
                |-- ...

Train from scratch

./scripts/train.sh ./configs/256x192_res50_regress-flow.yaml train_rle

Evaluation

Download the pretrained model from Google Drive.

./scripts/validate.sh ./configs/256x192_res50_regress-flow.yaml ./coco-laplace-rle.pth

Citing

If our code helps your research, please consider citing the following paper:

@inproceedings{li2021human,
    title={Human Pose Regression with Residual Log-likelihood Estimation},
    author={Li, Jiefeng and Bian, Siyuan and Zeng, Ailing and Wang, Can and Pang, Bo and Liu, Wentao and Lu, Cewu},
    booktitle={ICCV},
    year={2021}
}

Code for "Human Pose Regression with Residual Log-likelihood Estimation", ICCV 2021 Oral

Related tags

Overview

Human Pose Regression with Residual Log-likelihood Estimation

TODO

Installation

Train from scratch

Evaluation

Citing

Owner

JeffLi

The King is Naked: on the Notion of Robustness for Natural Language Processing

A python package for generating, analyzing and visualizing building shadows

AlgoVision - A Framework for Differentiable Algorithms and Algorithmic Supervision

Contra is a lightweight, production ready Tensorflow alternative for solving time series prediction challenges with AI

Gems & Holiday Package Prediction

Instance-based label smoothing for improving deep neural networks generalization and calibration

IsoGCN code for ICLR2021

Anomaly detection analysis and labeling tool, specifically for multiple time series (one time series per category)

ncnn is a high-performance neural network inference framework optimized for the mobile platform

Compartmental epidemic model to assess undocumented infections: applications to SARS-CoV-2 epidemics in Brazil - Datasets and Codes

Dataset and Source code of paper 'Enhancing Keyphrase Extraction from Academic Articles with their Reference Information'.

The description of FMFCC-A (audio track of FMFCC) dataset and Challenge resluts.

Pytorch implementation of SenFormer: Efficient Self-Ensemble Framework for Semantic Segmentation

Decompose to Adapt: Cross-domain Object Detection via Feature Disentanglement

Cooperative Driving Dataset: a dataset for multi-agent driving scenarios

Deep deconfounded recommender (Deep-Deconf) for paper "Deep causal reasoning for recommendations"

This repository contains notebook implementations of the following Neural Process variants: Conditional Neural Processes (CNPs), Neural Processes (NPs), Attentive Neural Processes (ANPs).

FastFCN: Rethinking Dilated Convolution in the Backbone for Semantic Segmentation.

A PyTorch implementation of DenseNet.

A Traffic Sign Recognition Project which can help the driver recognise the signs via text as well as audio. Can be used at Night also.