Multi-task Deep Learning for Real-Time 3D Human Pose Estimation and Action Recognition

Luvizon, Diogo C.; Picard, David; Tabia, Hedi

doi:10.1109/tpami.2020.2976014

Cited by 90 publications

(50 citation statements)

References 68 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…3. Inspired by multi-task deep learning [30], we first train the mask generator only with L BCE for 100 epochs. Then we freeze all parameters of the object detector and train the remaining network with L T otal for around 200 epochs.…”

Section: E Supervision Strategymentioning

confidence: 99%

Structure-Aware Dual-Branch Network for Electrical Impedance Tomography in Cell Culture Imaging

Chen

Yang

2021

IEEE Trans. Instrum. Meas.

View full text Add to dashboard Cite

Impedance Tomography (EIT) is an emerging imaging modality to monitor 3D cell culture dynamics through reconstructing the electrical properties of cell clusters.lectrical Impedance Tomography (EIT) is an emerging imaging modality to monitor 3D cell culture dynamics through reconstructing the electrical properties of cell clusters.E Recently, Machine Learning (ML) based approaches have achieved significant gains for the image reconstruction of EIT against conventional physical model based methods. However, continuous, multi-level conductivity distributions, which commonly exists in cell culture imaging, are more rigorous to reconstruct and remains challenging. This paper aims to tackle this challenge by proposing a structure-aware dual-branch deep learning method to predict both structure distribution and conductivity values. The proposed network comprises two independent branches to encode respectively the structure and conductivity features. The two branches are jointed later to make final predictions of conductivity distributions. Numerical and experimental evaluation results demonstrate the superior performance of the proposed method in dealing with the multi-level, continuous conductivity reconstruction problem.

show abstract

Section: E Supervision Strategymentioning

confidence: 99%

Structure-Aware Dual-Branch Network for Electrical Impedance Tomography in Cell Culture Imaging

Chen

Yang

2021

IEEE Trans. Instrum. Meas.

View full text Add to dashboard Cite

show abstract

“…In the work of Luvizon et al [55], they propose a multi-task framework for jointly estimating 2D or 3D human poses from monocular images. The architecture is composed of prediction blocks, downscaling and upscaling units, and simple connections.…”

Section: Fully-supervisedmentioning

confidence: 99%

Deep Learning Methods for 3D Human Pose Estimation under Different Supervision Paradigms: A Survey

Zhang

Guo

et al. 2021

Electronics

View full text Add to dashboard Cite

The rise of deep learning technology has broadly promoted the practical application of artificial intelligence in production and daily life. In computer vision, many human-centered applications, such as video surveillance, human-computer interaction, digital entertainment, etc., rely heavily on accurate and efficient human pose estimation techniques. Inspired by the remarkable achievements in learning-based 2D human pose estimation, numerous research studies are devoted to the topic of 3D human pose estimation via deep learning methods. Against this backdrop, this paper provides an extensive literature survey of recent literature about deep learning methods for 3D human pose estimation to display the development process of these research studies, track the latest research trends, and analyze the characteristics of devised types of methods. The literature is reviewed, along with the general pipeline of 3D human pose estimation, which consists of human body modeling, learning-based pose estimation, and regularization for refinement. Different from existing reviews of the same topic, this paper focus on deep learning-based methods. The learning-based pose estimation is discussed from two categories: single-person and multi-person. Each one is further categorized by data type to the image-based methods and the video-based methods. Moreover, due to the significance of data for learning-based methods, this paper surveys the 3D human pose estimation methods according to the taxonomy of supervision form. At last, this paper also enlists the current and widely used datasets and compares performances of reviewed methods. Based on this literature survey, it can be concluded that each branch of 3D human pose estimation starts with fully-supervised methods, and there is still much room for multi-person pose estimation based on other supervision methods from both image and video. Besides the significant development of 3D human pose estimation via deep learning, the inherent ambiguity and occlusion problems remain challenging issues that need to be better addressed.

show abstract

“…Mobile edge computing in video but used frame by frame as image, sensors of multifunctional simulated by smart phone to gather information from human body to recognize the activities in medical issue [29]. Monocular images extracted from video in 3D and 2D poses to verified from which activity was presented in [30]; the authors used two high parameters in still and video images. Random forest model was presented to enhance the deep learning, and 40 activities were recognized with good performance of HAR system [31].…”

Section: Literature Reviewmentioning

confidence: 99%

Weighted Classification of Machine Learning to Recognize Human Activities

Liu

Chen

2021

Complexity

View full text Add to dashboard Cite

This paper presents a new method to recognize human activities based on weighted classification for the features extracted by human body. Towards this end, new features depend on weight taken from image or video used in proposed descriptor. Human pose plays an important role in extracted features; then these features are used as the weight input with classifier. We use machine learning during two steps of training and testing images of standard dataset that can be used during benchmarking the system. Unlike previous methods that need size or length of shapes mainly to represent the cues when machine learning is used to recognize human activities, accurate experimental results coming from appropriate segments of the human body proved the worthiness of proposed method. Twelve activities are used in challenging of availability comparison with dataset to demonstrate our method. The results show that we achieved 87.3% in training set, while in testing set, we achieved 94% in terms of precision.

show abstract

Multi-task Deep Learning for Real-Time 3D Human Pose Estimation and Action Recognition

Cited by 90 publications

References 68 publications

Structure-Aware Dual-Branch Network for Electrical Impedance Tomography in Cell Culture Imaging

Structure-Aware Dual-Branch Network for Electrical Impedance Tomography in Cell Culture Imaging

Deep Learning Methods for 3D Human Pose Estimation under Different Supervision Paradigms: A Survey

Weighted Classification of Machine Learning to Recognize Human Activities

Contact Info

Product

Resources

About