Poselet Conditioned Pictorial Structures

By Leonid Pishchulin, Mykhaylo Andriluka, Peter Gehler, Bernt Schiele. 2013

365 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

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

Citations in the corpus

Towards Accurate Multi-person Pose Estimation in the Wild (2017, methodology): “well performing methods based on this idea is Deformable Part Model (DPM) by Felzenswalb et al. [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]. The majority of these methods focus on developing tractable inference ”
Realtime Multi-person 2D Pose Estimation Using Part Affinity Fields (2016, background): “Human 2D pose estimation—the problem of localizing anatomical keypoints or “parts”—has largely focused on finding body parts of individuals [8, 4, 3, 21, 33, 13, 25, 31, 6, 24].”
DeepPose: Human Pose Estimation via Deep Neural Networks (2013, methodology): “A different approach to capture higher-order relationship is through image-dependent PS models, which can be estimated via a global classiﬁer [26, 20, 18].”
Recent advances in convolutional neural networks (2015, methodology): “detector is a CNN based extension to the original Poselet [177] method.”
2D/3D Pose Estimation and Action Recognition Using Multitask Deep Learning (2018, background): “The problem of human pose estimation has been intensively studied in the last years, from Pictorial Structures [2, 17, 37] to more recent CNN approaches [34, 25, 38, 20, 41, 54, 5, 51, 52, 36].”
Human Pose Estimation with Iterative Error Feedback (2015, methodology): “Another line of work aims to inject class-specific spatial priors using coarse-to-fine processing, e.g. features arising from different layers of ConvNets were recently used for instance segmentation and keypoint prediction [15].”
Articulated Pose Estimation by a Graphical Model with Image Dependent Pairwise Relations (2014, methodology): “Conditional Random Fields (CRFs): Our model is also related to the conditional random field literature on data-dependent priors [18, 13, 15, 19].”
DeeperCut: A Deeper, Stronger, and Faster Multi-person Pose Estimation Model (2016, methodology): “ models such pairwise terms were essential for good performance [1,5,6]. Recent methods seem to prot less from such pairwise terms due to stronger unaries [8,10,11]. Image-conditioned pairwise terms [7,9] however have the promise to allow for better grouping. Last but not least, inference time is al”
P-CNN: Pose-Based CNN Features for Action Recognition (2015, positive): “While our pose estimator is imperfect, we use it to derive CNN-based pose features providing signiﬁcant improvements for action recognition for two challenging datasets.”
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 ”
Pose Machines: Articulated Pose Estimation via Inference Machines (2014, methodology): “Recent methods have also explored using part hierarchies [16,17] and condition the detection of smaller parts that model regions around anatomical joints on the localization of larger composite parts or poselets [11,10,18,19] that model limbs in canonical configurations and tend to be easier to dete”
Multi-source Deep Learning for Human Pose Estimation (2014, methodology): “There are also approaches that warp the part template by flexible sizes and orientations [12, 46, 39, 1, 40, 20, 44, 52].”
Deep Multitask Architecture for Integrated 2D and 3D Human Sensing (2017, methodology): “The problem of 2d human pose estimation has been approached initially using the pictorial structures and deformable part models where the kinematic tree structure of the human body offers a natural decomposition [11, 19, 7, 49, 29, 12].”