Learning Delicate Local Representations for Multi-person Pose Estimation

Cai, Yuanhao; Wang, Zhicheng; Luo, Zhaohui; Yin, Binyi; Du, Angang; Wang, Haoqian; Zhang, Xiangyu; Zhou, Xinyu; Zhou, Erjin; Sun, Jian

doi:10.1007/978-3-030-58580-8_27

Cited by 159 publications

(90 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Among the described architectures, top-down methods currently present the highest performance on HPE. For in-stance, MSPN [22] and RSN [5] The metric used to compute the distance between a person's prediction and its ground truth is the OKS (Equation 1).…”

Section: Multiperson Pose Estimationmentioning

confidence: 99%

DriPE: A Dataset for Human Pose Estimation in Real-World Driving Settings

Guesdon

Crispim-Junior

Tougne

2021

2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)

View full text Add to dashboard Cite

Section: Multiperson Pose Estimationmentioning

confidence: 99%

DriPE: A Dataset for Human Pose Estimation in Real-World Driving Settings

Guesdon

Crispim-Junior

Tougne

2021

2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)

View full text Add to dashboard Cite

“…Previous research in human pose estimation was built based on the idea of part-based models, which use different configurations of parts to represent a person [4]. Current methods of human pose estimation can be divided into two categories: top-down approaches [1][2][3][5][6][7][8][9][10][11][12][13][14] and bottom-up approaches [15][16][17][18][19][20]. Top-down approaches first obtain the position of the human body frame by a detector such as you only look once (YOLO) [21] or single shot multiBox detector (SSD) [22] and then detect the position of keypoints in the human region.…”

Section: Related Workmentioning

confidence: 99%

“…The high-resolution network (HR-Net) [2] maintained the spatial information of high-resolution features through lowresolution features and enabled high-resolution subnets to continuously obtain semantic information provided by low-resolution features through dense connections. In the residual steps network (RSN) [3], the intralevel pyramid features were integrated to extract more detailed local spatial information to obtain delicate local representations and accurately locate keypoints.…”

Section: Introductionmentioning

confidence: 99%

Multistage Polymerization Network for Multiperson Pose Estimation

Bai

Lei

2021

Journal of Sensors

View full text Add to dashboard Cite

Multiperson pose estimation is an important and complex problem in computer vision. It is regarded as the problem of human skeleton joint detection and solved by the joint heat map regression network in recent years. The key of achieving accurate pose estimation is to learn robust and discriminative feature maps. Although the current methods have made significant progress through interlayer fusion and intralevel fusion of feature maps, few works pay attention to the combination of the two methods. In this paper, we propose a multistage polymerization network (MPN) for multiperson pose estimation. The MPN continuously learns rich underlying spatial information by fusing features within the layers. The MPN also adds hierarchical connections between feature maps at the same resolution for interlayer fusion, so as to reuse low-level spatial information and refine high-level semantic information to obtain accurate keypoint representation. In addition, we observe a lack of connection between the output low-level information and the high-level information. To solve this problem, an effective shuffled attention mechanism (SAM) is proposed. The shuffle aims to promote the cross-channel information exchange between pyramid feature maps, while attention makes a trade-off between the low-level and high-level representations of the output features. As a result, the relationship between the space and the channel of the feature map is further enhanced. Evaluation of the proposed method is carried out on public datasets, and experimental results show that our method has better performance than current methods.

show abstract

“…The top-ranked models of the COCO key-point detection challenge set the state-ofthe-art in this field. These challenges have been conducted annually since 2016; the rankings of the best-performing models 5,6 changes annually as well. While ResNet-based models are still among the top-entries (regarding the average precision on the validation set) they are nowadays outperformed by other models, e.g., those defined by McNally et al [26], by Cai et al [6], and by Zhang et al [42].…”

Section: Related Workmentioning

confidence: 99%

“…com/ sota/ keypo int-detec tion-on-coco. 6 https:// paper swith code. com/ sota/ pose-estim ation-on-coco-test-dev.…”

Section: Related Workmentioning

confidence: 99%

Smoothing Skeleton Avatar Visualizations Using Signal Processing Technology

Gauss

Brandin²,

Heberle

et al. 2021

SN COMPUT. SCI.

View full text Add to dashboard Cite

Movements of a person can be recorded with a mobile camera and visualized as sequences of stick figures for assessments in health and elderly care, physio-therapy, and sports. However, since the visualizations flicker due to noisy input data, the visualizations themselves and even whole assessment applications are not trusted in general. The present paper evaluates different filters for smoothing the movement visualizations but keeping their validity for a visual physio-therapeutic assessment. It evaluates variants of moving average, high-pass, and Kalman filters with different parameters. Moreover, it presents a framework for the quantitative evaluation of smoothness and validity. As these two criteria are contradicting, the framework also allows to weight them differently and to automatically find the correspondingly best-fitting filter and its parameters. Different filters can be recommended for different weightings of smoothness and validity. The evaluation framework is applicable in more general contexts and with more filters than the three filters assessed. However, as a practical result of this work, a suitable filter for stick figure visualizations in a mobile application for assessing movement quality could be selected and used in a mobile app. The application is now more trustworthy and used by medical and sports experts, and end customers alike.

show abstract

Learning Delicate Local Representations for Multi-person Pose Estimation

Cited by 159 publications

References 30 publications

DriPE: A Dataset for Human Pose Estimation in Real-World Driving Settings

DriPE: A Dataset for Human Pose Estimation in Real-World Driving Settings

Multistage Polymerization Network for Multiperson Pose Estimation

Smoothing Skeleton Avatar Visualizations Using Signal Processing Technology

Contact Info

Product

Resources

About