Articulated pose estimation with flexible mixtures-of-parts

By Yi Yang, Deva Ramanan. 2011

1,214 citations recorded by the source corpus.

Subfields: 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 Computer Vision and Pattern Recognition

In Human-Computer Interaction

Citations in the corpus

Towards Accurate Multi-person Pose Estimation in the Wild (2017, methodology): “[15], which spurred a large body of work on probabilistic graphical models for 2-D human pose inference [3, 12, 39, 47, 11, 28, 34, 40, 18].”
Realtime Multi-person 2D Pose Estimation Using Part Affinity Fields (2016, methodology): “The spatial model for articulated pose is either based on tree-structured graphical models [10, 30, 4, 3, 26, 40, 17], which parametrically encode the spatial relationship between adjacent parts following a kinematic chain, or non-tree models [37, 31, 20, 18, 8] that augment the tree structure with…”
DeepPose: Human Pose Estimation via Deep Neural Networks (2013, background): “Yang and Ramanan [27] use a mixture model of parts.”
Joint Training of a Convolutional Network and a Graphical Model for Human Pose Estimation (2014, methodology): “Algorithms which model more complex joint relationships, such as Yang and Ramanan [37], use a ﬂexible mixture of templates modeled by linear SVMs. Johnson and Everingham [17] employ a cascade of body part detectors to obtain more discriminative templates.”
Detect What You Can: Detecting and Representing Objects Using Holistic Models and Body Parts (2014, methodology): “The recent works on human pose estimation [25, 16, 22, 20] typically do not consider the holistic object (root) template in their model as they are faced with highly variable poses.”
Large scale visual recommendations from street fashion images (2014, background): “We believe such methods are limited by their ability to accurately parse humans from real-world images since the problem of person detection and subsequent pose estimation is still largely unsolved [16].”
Recent advances in convolutional neural networks (2015, background): “Their classiﬁcation pipeline is composed of three types of attentions: the bottom-up attention proposes candidate patches, the object-level top-down attention selects relevant patches of a certain object, and the part-level top-down attention localizes discriminative parts.”
Space-Time Representation of People Based on 3D Skeletal Data: A Review (2016, methodology): “Methods based on a single image: Many algorithms were proposed to construct human skeletal model using a single color or intensity image acquired from a monocular camera [65], [68], [69], [89].”
Spatio-Temporal LSTM with Trust Gates for 3D Human Action Recognition (2016, positive): “In human parsing, skeletal joints are popularly modeled as a tree-based pictorial structure [55,56], as illustrated in Fig.”
Learning Category-Specific Mesh Reconstruction from Image Collections (2018, methodology): “Lastly, we can also measure our keypoint reprojection accuracy using the percentage of correct keypoints (PCK) metric [36].”
Human Pose Estimation with Iterative Error Feedback (2015, methodology): “We will use as running example the task of 2D human pose estimation [48, 39, 37, 28], where the goal is to infer the 2D locations of a set of keypoints such as wrists, ankles, etc, from a single RGB image.”
Single Image 3D Interpreter Network (2016, methodology): “Our method performs better than all previous methods [34,44,43,55,47] at all precisions.”
Video In Sentences Out (2012, background): “…far noisier and less accurate than fitting precise articulated models (Andriluka et al., 2008; Bregler, 1997; Gavrila and Davis, 1995; Sigal et al., 2010; Yang and Ramanan, 2011) and appears unintelligible to the human eye, as shown in Section 3.3, it suffices to improve event-recognition accuracy.”
Picture: A probabilistic programming language for scene perception (2015, methodology): “On the given dataset, as shown in the error histogram in (a) , our model is more accurate on average than just using the DPM based human pose detector [48].”
Articulated Human Detection with Flexible Mixtures of Parts (2013, background): “Overview: An earlier version of this manuscript appeared in [10].”