RMPE: Regional Multi-person Pose Estimation (2016-12-01T00:00:00.000000Z)

TL;DR

This paper proposes a novel regional multi-person pose estimation (RMPE) framework to facilitate pose estimation in the presence of inaccurate human bounding boxes and can achieve 76:7 mAP on the MPII (multi person) dataset.

Abstract

Multi-person pose estimation in the wild is challenging. Although state-of-the-art human detectors have demonstrated good performance, small errors in localization and recognition are inevitable. These errors can cause failures for a single-person pose estimator (SPPE), especially for methods that solely depend on human detection results. In this paper, we propose a novel regional multi-person pose estimation (RMPE) framework to facilitate pose estimation in the presence of inaccurate human bounding boxes. Our framework consists of three components: Symmetric Spatial Transformer Network (SSTN), Parametric Pose Non-Maximum-Suppression (NMS), and Pose-Guided Proposals Generator (PGPG). Our method is able to handle inaccurate bounding boxes and redundant detections, allowing it to achieve 76:7 mAP on the MPII (multi person) dataset[3]. Our model and source codes are made publicly available.

Authors

Haoshu Fang

14 papers

Yu-Wing Tai

27 papers

Cewu Lu

7 papers

TL;DR

Abstract

Authors

References55 items

Cascaded Pyramid Network for Multi-person Pose Estimation

Learning Feature Pyramids for Human Pose Estimation

Soft-NMS — Improving Object Detection with One Line of Code

Mask R-CNN

An Implementation of Faster RCNN with Study for Region Sampling

Towards Accurate Multi-person Pose Estimation in the Wild

ArtTrack: Articulated Multi-Person Tracking in the Wild

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

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

Joint Graph Decomposition & Node Labeling: Problem, Algorithms, Applications

Multi-person Pose Estimation with Local Joint-to-Person Associations

Recurrent Human Pose Estimation

DeeperCut: A Deeper, Stronger, and Faster Multi-person Pose Estimation Model

Stacked Hourglass Networks for Human Pose Estimation

SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <1MB model size

Convolutional Pose Machines

Deep Residual Learning for Image Recognition

SSD: Single Shot MultiBox Detector

Attributed Grammars for Joint Estimation of Human Attributes, Part and Pose

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

Spatial Transformer Networks

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

Fast R-CNN

Combining local appearance and holistic view: Dual-Source Deep Neural Networks for human pose estimation

Parsing occluded people by flexible compositions

Human Pose Estimation with Fields of Parts

Using k-Poselets for Detecting People and Localizing Their Keypoints

Towards Unified Human Parsing and Pose Estimation

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

Multi-source Deep Learning for Human Pose Estimation

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

Learning Human Pose Estimation Features with Convolutional Networks

DeepPose: Human Pose Estimation via Deep Neural Networks

Strong Appearance and Expressive Spatial Models for Human Pose Estimation

Articulated Human Detection with Flexible Mixtures of Parts

Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation

Merging Pose Estimates Across Space and Time

Computationally Efficient Regression on a Dependency Graph for Human Pose Estimation

Human Pose Estimation Using a Joint Pixel-wise and Part-wise Formulation

Human Pose Estimation Using Body Parts Dependent Joint Regressors

Beyond Physical Connections: Tree Models in Human Pose Estimation

An efficient branch-and-bound algorithm for optimal human pose estimation

Articulated people detection and pose estimation: Reshaping the future

Conditional regression forests for human pose estimation

Cascaded Models for Articulated Pose Estimation

We Are Family: Joint Pose Estimation of Multiple Persons

Efficient human pose estimation via parsing a tree structure based human model

Et al

Multiple Tree Models for Occlusion and Spatial Constraints in Human Pose Estimation

Context and observation driven latent variable model for human pose estimation

Signature Verification Using A "Siamese" Time Delay Neural Network

Jonas Uhrig

MSCOCO keypoint challenge

I and J

Ieee Transactions on Pattern Analysis and Machine Intelligence 1 Recognizing Human-object Interactions in Still Images by Modeling the Mutual Context of Objects and Human Poses

Field of Study

Journal Information

Name

Page

Venue Information

Name

Type

URL

Alternate Names