Articulated Pose Estimation by a Graphical Model with Image Dependent Pairwise Relations

By Xianjie Chen, Alan L. Yuille. 2014

530 citations recorded by the source corpus.

We present a method for estimating articulated human pose from a single static image based on a graphical model with novel pairwise relations that make adaptive use of local image measurements. More precisely, we specify a graphical model for human pose which exploits the fact the local image measurements can be used both to detect parts (or joints) and also to predict the spatial relationships between them (Image Dependent Pairwise Relations). These spatial relationships are represented by a mixture model. We use Deep Convolutional Neural Networks (DCNNs) to learn conditional probabilities for the presence of parts and their spatial relationships within image patches. Hence our model combines the representational flexibility of graphical models with the efficiency and statistical power of DCNNs. Our method significantly outperforms the state of the art methods on the LSP and FLIC datasets and also performs very well on the Buffy dataset without any training.

Subfields: Computer Vision and Pattern Recognition, Model Architectures

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Model Architectures

Citations in the corpus

Towards Accurate Multi-person Pose Estimation in the Wild (2017, background): “Chen et al. [10] added image-dependant priors to improve CNN performance.”
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].”
Minding the Gaps for Block Frank-Wolfe Optimization of Structured SVMs (2016, methodology): “We build our model based on the one by Kolesnikov et al. (2014) for HorseSeg, and the one by Chen & Yuille (2014) for LSP.”
Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs (2014, background): “While this invariance is clearly desirable for high-level vision tasks, it can hamper low-level tasks, such as pose estimation (Chen & Yuille, 2014; Tompson et al., 2014) and semantic segmentation - where we want precise localization, rather than abstraction of spatial details.”
Stacked Hourglass Networks for Human Pose Estimation (2016, background): “[25] cluster detections into typical orientations so that when their classifier makes predictions additional information is available indicating the likely location of a neighboring joint.”
Recent advances in convolutional neural networks (2015, methodology): “[151], [152] also combine graphical model with CNN.”
Feature Boosting Network For 3D Pose Estimation (2019, background): “[23] proposed a graphical model of the body joints as a post-processing step.”
Efficient object localization using Convolutional Networks (2014, methodology): “The model of Toshev et al. [22] significantly output-performed state-of-art methods on the challenging ‘FLIC’ [20] dataset and was competitive on the ‘LSP’ [16] dataset.”
Human Pose Estimation with Iterative Error Feedback (2015, background): “Graphical models can also encode dependencies between outputs and are still popular in many applications, including human pose estimation [5].”
DeeperCut: A Deeper, Stronger, and Faster Multi-person Pose Estimation Model (2016, methodology): “Recent work aimed to incorporate convolutional detectors into part-based models [9] or design stronger detectors by combining the detector output with location-based features [20].”
P-CNN: Pose-Based CNN Features for Action Recognition (2015, background): “Application of CNNs to action recognition in video, however, has shown only limited improvements so far [30, 39].”
Recurrent Human Pose Estimation (2016, methodology): “The outcome of our approach is a simple recurrent model that reaches state-of-the-art performance on different standard benchmark datasets, but does not employ an explicit configuration model [10] nor a complicated network architecture [37].”
Deep High-Resolution Representation Learning for Human Pose Estimation (2019, background): “Most traditional solutions to single-person pose estimation adopt the probabilistic graphical model or the pictorial structure model [76, 49], which is recently improved by exploiting deep learning for better modeling the unary and pair-wise energies [9, 63, 44] or imitating the iterative inference ”
LCR-Net: Localization-Classiﬁcation-Regression for Human Pose (unknown): “Most state-of-the-art approaches for 2D human pose estimation employ CNNs [4, 6, 8, 14, 15, 19, 20, 30, 31].”
Pose for Action - Action for Pose (2016, methodology): “Several approaches have been proposed to improve the accuracy of PS models for human pose estimation.”
HICO: A Benchmark for Recognizing Human-Object Interactions in Images (2015, background): “Despite significant advances in recognizing humans [2] and objects [14], the state of the art of HOI recognition in images is still far from the demands of real-world applications.”
LCR-Net++: Multi-Person 2D and 3D Pose Detection in Natural Images (2018, background): “Most state-of-the-art approaches for 2D human pose estimation employ CNN architectures [1], [2], [3], [13], [17], [18], [19], [20].”