Simple Baselines for Human Pose Estimation and Tracking (2018-04-17T00:00:00.000000Z)

TL;DR

This work provides simple and effective baseline methods for pose estimation that are helpful for inspiring and evaluating new ideas for the field and achieved on challenging benchmarks.

Abstract

There has been significant progress on pose estimation and increasing interests on pose tracking in recent years. At the same time, the overall algorithm and system complexity increases as well, making the algorithm analysis and comparison more difficult. This work provides simple and effective baseline methods. They are helpful for inspiring and evaluating new ideas for the field. State-of-the-art results are achieved on challenging benchmarks. The code will be available at this https URL.

Authors

Bin Xiao

6 papers

Yichen Wei

9 papers

Haiping Wu

1 papers

TL;DR

Abstract

Authors

References41 items

Pose Flow: Efficient Online Pose Tracking

Detect-and-Track: Efficient Pose Estimation in Videos

Cascaded Pyramid Network for Multi-person Pose Estimation

PoseTrack: A Benchmark for Human Pose Estimation and Tracking

Learning Feature Pyramids for Human Pose Estimation

Self Adversarial Training for Human Pose Estimation

Adversarial PoseNet: A Structure-Aware Convolutional Network for Human Pose Estimation

Flow-Guided Feature Aggregation for Video Object Detection

Mask R-CNN

Deformable Convolutional Networks

Multi-context Attention for Human Pose Estimation

Towards Accurate Multi-person Pose Estimation in the Wild

FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks

Realtime Multi-person 2D Pose Estimation Using Part Affinity Fields

Deep Feature Flow for Video Recognition

Associative Embedding: End-to-End Learning for Joint Detection and Grouping

R-FCN: Object Detection via Region-based Fully Convolutional Networks

Stacked Hourglass Networks for Human Pose Estimation

Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning

Deep Residual Learning for Image Recognition

MXNet: A Flexible and Efficient Machine Learning Library for Heterogeneous Distributed Systems

DeepCut: Joint Subset Partition and Labeling for Multi Person Pose Estimation

Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks

Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift

Adam: A Method for Stochastic Optimization

ImageNet Large Scale Visual Recognition Challenge

Joint Training of a Convolutional Network and a Graphical Model for Human Pose Estimation

2D Human Pose Estimation: New Benchmark and State of the Art Analysis

Microsoft COCO: Common Objects in Context

DeepPose: Human Pose Estimation via Deep Neural Networks

ImageNet classification with deep convolutional neural networks

Evaluating Multiple Object Tracking Performance: The CLEAR MOT Metrics

Pose ﬂow: Eﬃcient online pose tracking arXiv preprint arXiv:1802.00977

flownet2-pytorch

NVIDIA

Multi-Person Pose Estimation for PoseTrack with Enhanced Part Affinity Fields

Towards Multi-Person Pose Tracking : Bottom-up and Top-down Methods

COCO Leader Board

Kernel size. Methods (a, c, d

As in most vision

size. Methods (a, c, d) show that a smaller kernel size gives a marginally decrease in AP, which is 0.3 point decrease from kernel size 4 to 2. By default, deconvolution kernel size of 4 is used

Field of Study

Journal Information

Name

Volume

Venue Information

Name

Type

URL

Alternate Names