DeepPose: Human Pose Estimation via Deep Neural Networks
By Alexander Toshev, Christian Szegedy. 2013
3,089 citations recorded by the source corpus.
We propose a method for human pose estimation based on Deep Neural Networks (DNNs). The pose estimation is formulated as a DNN-based regression problem towards body joints. We present a cascade of such DNN regres- sors which results in high precision pose estimates. The approach has the advantage of reasoning about pose in a holistic fashion and has a simple but yet powerful formula- tion which capitalizes on recent advances in Deep Learn- ing. We present a detailed empirical analysis with state-of- art or better performance on four academic benchmarks of diverse real-world images.
Subfields: Biomedical Engineering, Computer Vision and Pattern Recognition, Human-Computer Interaction
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Biomedical Engineering
- Yi Yang
- Wanli Ouyang
- Xiaogang Wang
- Juergen Gall
- Jitendra Malik
- Cordelia Schmid
- Liang Zheng
- Andrew Zisserman
In Computer Vision and Pattern Recognition
- Luc Van Gool
- Dacheng Tao
- Xiaogang Wang
- Jitendra Malik
- Ming-Hsuan Yang
- Trevor Darrell
- Andrew Zisserman
- Yi Yang
In Human-Computer Interaction
- Yichen Wei
- Cordelia Schmid
- Bin Xiao
- Jitendra Malik
- Yaser Sheikh
- Xiaogang Wang
- Michael J. Black
- Kostas Daniilidis
Citations in the corpus
- Rethinking the Inception Architecture for Computer Vision (2015, background): “…[16] winning entry by Krizhevsky et al [9], their network “AlexNet” has been successfully applied to a larger variety of computer vision tasks, for example to object-detection [5], segmentation [12], human pose estimation [22], video classification [8], object tracking [23], and superresolution [3].”
- Going deeper with convolutions (2014, methodology): “f accurate spatial information, the same convolutional network architecture as [9] has also been successfully employed for localization [9, 14], object detection [6,14,18,5] and human pose estimation [19]. Inspired by a neuroscience model of the primate visual cortex, Serre et al. [15] use a series ”
- Stochastic Optimization of Plain Convolutional Neural Networks with Simple Methods (2020, background): “Deep Learning has the main rule of the improvement in the field of computer vision, resulting in state-of-the-art performance in many challenging tasks [4], such as object recognition [2], semantic segmentation [1], image captioning [11], and human pose estimation [12].”
- Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning (2016, methodology): “Since the 2012 ImageNet competition [11] winning entry by Krizhevsky et al [8], their network “AlexNet” has been successfully applied to a larger variety of computer vision tasks, for example to object-detection [4], segmentation [10], human pose estimation [17], video classification [7], object tra”
- Objects as Points (2019, neutral): “[51] and Sun et al .”
- Hypercolumns for object segmentation and fine-grained localization (2014, methodology): “This is different from most prior work on these problems [38, 37, 41, 40, 3, 31], which operates on the immediate vicinity of ground-truth instances.”
- Towards Accurate Multi-person Pose Estimation in the Wild (2017, methodology): “One approach would be to use a single regressor per key-point, as in [43], but this is problematic when there is more than one person in the image patch (in which case a key-point can occur in multiple places).”
- Beyond Skip Connections: Top-Down Modulation for Object Detection (2016, methodology): “After the resurgence of ConvNets for image classification [8, 29], they have been successfully adopted for a variety of computer vision tasks such as object detection [16, 17, 41, 48], semantic segmentation [3, 6, 34, 35], instance segmentation [21, 22, 38], pose estimation [49, 50], depth estimatio”
- Realtime Multi-person 2D Pose Estimation Using Part Affinity Fields (2016, methodology): “To obtain reliable local observations of body parts, Convolu-tional Neural Networks (CNNs) have been widely used, and have significantly boosted the accuracy on body pose estimation [23, 38, 24, 34, 35, 7, 36, 6].”
- Convolutional Pose Machines (2016, methodology): “[6] train a deep network that iteratively improves part detections using error feedback but use a cartesian representation as in [40] which does not preserve spatial uncertainty and results in lower accuracy in the highprecision regime.”
- Perceiver IO: A General Architecture for Structured Inputs & Outputs (2021, background): “As hardware acceleration grew more powerful and neural nets proved themselves in image understanding [41, 101, 78], interest intensified: autoregressive models were developed that could take samples of handwriting and complete them [28], and new convolutional network designs led to good results in s”
- Improved Regularization of Convolutional Neural Networks with Cutout (2017, background): “In recent years deep learning has contributed to considerable advances in the field of computer vision, resulting in state-of-the-art performance in many challenging vision tasks such as object recognition [8], semantic segmentation [11], image captioning [19], and human pose estimation [17].”
- Speeding up Convolutional Neural Networks with Low Rank Expansions (2014, background): “The combination of an endto-end learning system with minimal need for human design decisions, and the ability to efficiently train large and complex models, have allowed them to achieve state-of-the-art performance in a number of benchmarks [10, 14, 19, 33, 37, 38].”
- Squeeze-and-Excitation Networks (2017, background): “Convolutional neural networks (CNNs) have proven to be effective models for tackling a variety of visual tasks [21, 27, 33, 45].”
- CNN Features Off-the-Shelf: An Astounding Baseline for Recognition (2014, background): “Finally, we have to point out that, given enough computational resources, optimizing the CNN features for specific tasks/datasets would probably boost the performance of the simplistic system even further [29, 15, 51, 43, 41].”
- Visual7W: Grounded Question Answering in Images (2015, background): “The recent development of deep learning technologies has achieved successes in many perceptual visual tasks such as object recognition, image classification and pose estimation [15, 21, 25, 38, 39, 42, 43].”
- Joint Training of a Convolutional Network and a Graphical Model for Human Pose Estimation (2014, background): “Toshev et al. [36] show state-of-art performance on the ‘FLIC’ [29] and ‘LSP’ [18] datasets.”
- Stacked Hourglass Networks for Human Pose Estimation (2016, background): “reduced from 4.7% to 1.8%. For MPII, we see a 2-3% improvement across dicult joints up from the most recently available results. 1 2 Related Work With the introduction of ‘DeepPose’ by Toshev et al. [24], research on human pose estimation started to shift from the classic approaches [2,3,4,1,5,6,7,8”
- UberNet: Training a Universal Convolutional Neural Network for Low-, Mid-, and High-Level Vision Using Diverse Datasets and Limited Memory (2016, background): “…[14, 27,67], region proposal generation [30,82,85], instance segmentation [21, 37, 82], pose estimation, part segmentation, and landmark localization [3,15,42,75,81,96,98,104,111], as well as the large body of works around object detection and image classification e.g. [22,31,32,40,52,85,89,93,94].”