Published on Wed Apr 14 2021

Pose Recognition with Cascade Transformers

Ke Li, Shijie Wang, Xiang Zhang, Yifan Xu, Weijian Xu, Zhuowen Tu
0
0
0
Abstract

In this paper, we present a regression-based pose recognition method using cascade Transformers. One way to categorize the existing approaches in this domain is to separate them into 1). heatmap-based and 2). regression-based. In general, heatmap-based methods achieve higher accuracy but are subject to various heuristic designs (not end-to-end mostly), whereas regression-based approaches attain relatively lower accuracy but they have less intermediate non-differentiable steps. Here we utilize the encoder-decoder structure in Transformers to perform regression-based person and keypoint detection that is general-purpose and requires less heuristic design compared with the existing approaches. We demonstrate the keypoint hypothesis (query) refinement process across different self-attention layers to reveal the recursive self-attention mechanism in Transformers. In the experiments, we report competitive results for pose recognition when compared with the competing regression-based methods.

Thu Mar 18 2021
Machine Learning
OmniPose: A Multi-Scale Framework for Multi-Person Pose Estimation
0
0
0
Mon Nov 20 2017
Computer Vision
Cascaded Pyramid Network for Multi-Person Pose Estimation
Cascaded Pyramid Network targets to relieve the problem from these "hard" keypoints. Algorithm includes two stages: GlobalNet and RefineNet. Based on proposed algorithm, we achieve state-of-art results on the COCO keypoint benchmark.
0
0
0
Mon Oct 14 2019
Computer Vision
Multi-Stage HRNet: Multiple Stage High-Resolution Network for Human Pose Estimation
Human pose estimation is of importance for visual understanding tasks such as action recognition and human-computer interaction. We present a Multiple Stage High-Resolution Network (Multi-Stage HRNet) to tackling the problem of multi-person pose estimation in images.
0
0
0
Wed Jan 27 2021
Computer Vision
Multi-Hypothesis Pose Networks: Rethinking Top-Down Pose Estimation
A key assumption of top-down human pose estimation approaches is their expectation of having a single person present in the input bounding box. We propose a novel solution to overcome the limitations of this fundamental assumption. Our Multi-Hypothesis Pose Network (MHPNet) allows for predicting multiple 2
2
2
5
Tue Apr 06 2021
Computer Vision
Bottom-Up Human Pose Estimation Via Disentangled Keypoint Regression
The proposed direct regression method outperforms keypoint detection and grouping methods. It achieves superior bottom-up pose estimation results on two benchmark datasets, COCO and CrowdPose. The code and models are available at https://github.com/HRNet/DEKR.
1
0
1
Tue Mar 17 2020
Computer Vision
Augmented Parallel-Pyramid Net for Attention Guided Pose-Estimation
The target of human pose estimation is to determine body part or joint locations of each person from an image. To address this issue, this paper proposes an augmented parallel-pyramid net with attention partial module and differentiable auto-data augmentation.
0
0
0