Mutual Information-Based Temporal Difference Learning for Human Pose Estimation in Video

Feng, Runyang; Gao, Yixing; Ma, Xueqing; Tse, Tze Ho Elden; Chang, Hyung Jin

doi:10.1109/cvpr52729.2023.01643

Cited by 10 publications

(3 citation statements)

References 54 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Bottom-Up methods [12,13] first detect individual body parts and then compose these detection gesture points into a whole person. On the other hand, the Top-Down approach [14,15,16] first detects the human body bounding box and then detects the human body pose within each bounding box.…”

Section: Related Workmentioning

confidence: 99%

Adaptive Target Region Attention Network-based Human Pose Estimation in Smart Classroom

Mo,

Jiang,

Yuan

et al. 2024

IJACSA

View full text Add to dashboard Cite

In smart classroom environments, problems such as occlusion and overlap make the acquisition of student pose information challenging. To address these problems, a lightweight human pose estimation model with Adaptive Target Region Attention based on Lite-HRNet is proposed for smart classroom scenarios. Firstly, the Deformable Convolutional Encoding Network (DCEN) module is designed to reconstruct the encoding of features through an encoder and then a multi-layer deformable convolutional module is used to adaptively focus on the image region to obtain a feature representation that focuses on the target region of interest of the student subject. Secondly, the Channel And Spatial Attention (CASA) module is designed to attenuate or enhance the feature attention in different regions of the feature map to obtain a more accurate representation of the target feature. Finally, extensive experiments were conducted on the COCO dataset and the smart classroom dataset (SC-Data) to compare the proposed model with the current main popular human pose estimation framework. The experimental results show that the performance of the model reaches 67.5(mAP) in the COCO dataset, which is an improvement of 2.7(mAP) compared to the Lite-HRNet model, and 86.6(mAP) in the SC-Data dataset, which is an improvement of 1.6(mAP) compared to the Lite-HRNet model.

show abstract

Section: Related Workmentioning

confidence: 99%

Adaptive Target Region Attention Network-based Human Pose Estimation in Smart Classroom

Mo,

Jiang,

Yuan

et al. 2024

IJACSA

View full text Add to dashboard Cite

show abstract

“…Recently, Liu et al [18] proposed a deep Dual Consecutive Pose (DCPose) model for pose prediction that addressed motion blur and pose occlusion problems. Similarly, the TDMI model [151] overcomes the blur and occlusion problem by exploiting the temporal difference information of the video frame. Ruan et al [152] proposed an end-to-end network called Pose-Guided Ovonic Insight Network (POINet) that provides a multistage process consisting of feature extraction, similarity estimation, and identity assignment as a unified network.…”

Section: Offline Approachmentioning

confidence: 99%

“…Table 17 summarizes the methodologies of the offline approach, while Table 18 shows their performance. [154] 2019 HRNet -77.9 -DCPose [18] 2021 HRNet 384 × 288 79.2 -TDMI-ST [151] 2023 --85.9 * -…”

Section: Offline Approachmentioning

confidence: 99%

Human Pose Estimation Using Deep Learning: A Systematic Literature Review

Samkari,

Arif,

Alghamdi

et al. 2023

MAKE

View full text Add to dashboard Cite

Human Pose Estimation (HPE) is the task that aims to predict the location of human joints from images and videos. This task is used in many applications, such as sports analysis and surveillance systems. Recently, several studies have embraced deep learning to enhance the performance of HPE tasks. However, building an efficient HPE model is difficult; many challenges, like crowded scenes and occlusion, must be handled. This paper followed a systematic procedure to review different HPE models comprehensively. About 100 articles published since 2014 on HPE using deep learning were selected using several selection criteria. Both image and video data types of methods were investigated. Furthermore, both single and multiple HPE methods were reviewed. In addition, the available datasets, different loss functions used in HPE, and pretrained feature extraction models were all covered. Our analysis revealed that Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) are the most used in HPE. Moreover, occlusion and crowd scenes remain the main problems affecting models’ performance. Therefore, the paper presented various solutions to address these issues. Finally, this paper highlighted the potential opportunities for future work in this task.

show abstract

Self-supervised Siamese keypoint inference network for human pose estimation and tracking

Wang,

Tian,

Wang

2024

Machine Vision and Applications

View full text Add to dashboard Cite

Mutual Information-Based Temporal Difference Learning for Human Pose Estimation in Video

Cited by 10 publications

References 54 publications

Adaptive Target Region Attention Network-based Human Pose Estimation in Smart Classroom

Adaptive Target Region Attention Network-based Human Pose Estimation in Smart Classroom

Human Pose Estimation Using Deep Learning: A Systematic Literature Review

Self-supervised Siamese keypoint inference network for human pose estimation and tracking

Contact Info

Product

Resources

About