SimCC: A Simple Coordinate Classification Perspective for Human Pose Estimation

Li, Yanjie; Yang, Sen; Liu, Peidong; Shoukui, Zhang,; Wang, Yunxiao; Wang, Zhicheng; Yang, Wankou; Xia, Shu-Tao

doi:10.1007/978-3-031-20068-7_6

Cited by 87 publications

(42 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, the true resolution of the target area is low, the accuracy of the heatmap is reduced, and there is a feature shift in the feature layers of different scales, which increases the uncertainty of the key-point location. For example, if two key points of the same category are close to each other, they may be mistaken for the same key point due to overlapping heatmap signals, leading to key-point detection failure and affecting the final recognition effect [ 42 , 43 ]. Given the obvious shortcomings of the heatmap, this work calibrates the human body and joints based on YOLOv5, does not use a heatmap, and contains an efficient network design.…”

Section: Methodsmentioning

confidence: 99%

Optically Non-Contact Cross-Country Skiing Action Recognition Based on Key-Point Collaborative Estimation and Motion Feature Extraction

et al. 2023

Sensors

View full text Add to dashboard Cite

Technical motion recognition in cross-country skiing can effectively help athletes to improve their skiing movements and optimize their skiing strategies. The non-contact acquisition method of the visual sensor has a bright future in ski training. The changing posture of the athletes, the environment of the ski resort, and the limited field of view have posed great challenges for motion recognition. To improve the applicability of monocular optical sensor-based motion recognition in skiing, we propose a monocular posture detection method based on cooperative detection and feature extraction. Our method uses four feature layers of different sizes to simultaneously detect human posture and key points and takes the position deviation loss and rotation compensation loss of key points as the loss function to implement the three-dimensional estimation of key points. Then, according to the typical characteristics of cross-country skiing movement stages and major sub-movements, the key points are divided and the features are extracted to implement the ski movement recognition. The experimental results show that our method is 90% accurate for cross-country skiing movements, which is equivalent to the recognition method based on wearable sensors. Therefore, our algorithm has application value in the scientific training of cross-country skiing.

show abstract

Section: Methodsmentioning

confidence: 99%

Optically Non-Contact Cross-Country Skiing Action Recognition Based on Key-Point Collaborative Estimation and Motion Feature Extraction

et al. 2023

Sensors

View full text Add to dashboard Cite

show abstract

“…Discretization errors are also introduced to the targets. Yet for a diverse set of regression problems, including depth estimation (Cao et al, 2017), age estimation (Rothe et al, 2015), crowd-counting (Liu et al, 2019a) and keypoint detection (Li et al, 2022), classification yields better performance.…”

Section: Introductionmentioning

confidence: 99%

Improving Deep Regression with Ordinal Entropy

Zhang¹,

Yang²,

Mi³

et al. 2023

Preprint

View full text Add to dashboard Cite

In computer vision, it is often observed that formulating regression problems as a classification task yields better performance. We investigate this curious phenomenon and provide a derivation to show that classification, with the cross-entropy loss, outperforms regression with a mean squared error loss in its ability to learn high-entropy feature representations. Based on the analysis, we propose an ordinal entropy regularizer to encourage higher-entropy feature spaces while maintaining ordinal relationships to improve the performance of regression tasks. Experiments on synthetic and real-world regression tasks demonstrate the importance and benefits of increasing entropy for regression.

show abstract

“…The model-based methods mostly take human poses (i.e., keypoints) as the input which encodes visual clues for body structure and proportion in an explicit way. Benefiting from the rapid development in pose estimation [2,7,16,28] and graph-based models (GCN [27,35] and Transformer [23]), the pose-based methods have achieved fairly surprising results in some cases [30,31,37], e.g., GaitTR [37] introduces Spatial Transformer to establish overall spatial relationships between keypoints. The model achieves much higher accuracy than previous pose-based methods [30,31] on CASIA-B [36], even surpassing the accuracy of appearance-based methods [4,6,11,20] in conditions where the subject wears a coat.…”

Section: Introductionmentioning

confidence: 99%

GPGait: Generalized Pose-based Gait Recognition

Fu¹,

Shibei²,

Hou³

et al. 2023

Preprint

View full text Add to dashboard Cite

Recent works on pose-based gait recognition have demonstrated the potential of using such simple information to achieve results comparable to silhouette-based methods. However, the generalization ability of pose-based methods on different datasets is undesirably inferior to that of silhouette-based ones, which has received little attention but hinders the application of these methods in real-world scenarios. To improve the generalization ability of pose-based methods across datasets, we propose a Generalized Pose-based Gait recognition (GPGait) framework. First, a Human-Oriented Transformation (HOT) and a series of Human-Oriented Descriptors (HOD) are proposed to obtain a unified pose representation with discriminative multi-features. Then, given the slight variations in the unified representation after HOT and HOD, it becomes crucial for the network to extract local-global relationships between the keypoints. To this end, a Part-Aware Graph Convolutional Network (PAGCN) is proposed to enable efficient graph partition and local-global spatial feature extraction. Experiments on four public gait recognition datasets, CASIA-B, OUMVLP-Pose, Gait3D and GREW, show that our model demonstrates better and more stable cross-domain capabilities compared to existing skeletonbased methods, achieving comparable recognition results to silhouette-based ones. The code will be released.

show abstract

SimCC: A Simple Coordinate Classification Perspective for Human Pose Estimation

Cited by 87 publications

References 33 publications

Optically Non-Contact Cross-Country Skiing Action Recognition Based on Key-Point Collaborative Estimation and Motion Feature Extraction

Optically Non-Contact Cross-Country Skiing Action Recognition Based on Key-Point Collaborative Estimation and Motion Feature Extraction

Improving Deep Regression with Ordinal Entropy

GPGait: Generalized Pose-based Gait Recognition

Contact Info

Product

Resources

About